Upload 10 files

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "../MistralModels/models/Jamba-small",
+  "architectures": [
+    "JambaForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_layer_offset": 4,
+  "attn_layer_period": 8,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "expert_layer_offset": 1,
+  "expert_layer_period": 2,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_state": 16,
+  "mamba_dt_rank": 32,
+  "mamba_expand": 2,
+  "mamba_proj_bias": false,
+  "max_position_embeddings": 4096,
+  "model_type": "jamba",
+  "num_attention_heads": 8,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 2,
+  "num_logits_to_keep": 1,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "use_mamba_kernels": true,
+  "vocab_size": 4096
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97cece7f9f8960cc542f91abb9d963e45d6f759245e64673392fb0461569246
+size 228483488

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e63f0239703cb148641045068288cfdafb6c4259658dba9c760aa93674cb05
+size 457229739

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a2aa7bca84d2b8e7dd4e04a286714ba9169af11c46c739950a52df4c45259f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:814d10557c7a1fe194ef4383f09fb0496a267bb5b854cc24e0cc5ffb6b44b0e6
+size 1064

tokenizer_config.json

@@ -0,0 +1 @@
+{"tokenizer_class": "PreTrainedTokenizerFast", "unk_token": "[UNK]", "cls_token": "[CLS]", "sep_token": "[SEP]", "pad_token": "[PAD]", "mask_token": "[MASK]"}

trainer_state.json

@@ -0,0 +1,227 @@
+{
+  "best_metric": 5.311040878295898,
+  "best_model_checkpoint": "./results/models/checkpoint-7923",
+  "epoch": 18.999925065567627,
+  "eval_steps": 500,
+  "global_step": 7923,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5994754589733983,
+      "grad_norm": 0.078125,
+      "learning_rate": 0.001976019184652278,
+      "loss": 3.2965,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.877610206604004,
+      "eval_runtime": 923.3363,
+      "eval_samples_per_second": 2.166,
+      "eval_steps_per_second": 1.083,
+      "step": 835
+    },
+    {
+      "epoch": 1.1978269014612215,
+      "grad_norm": 0.0546875,
+      "learning_rate": 0.0019520383693045565,
+      "loss": 2.9688,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7973023604346197,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.0019280575539568346,
+      "loss": 2.8777,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.635538101196289,
+      "eval_runtime": 917.0438,
+      "eval_samples_per_second": 2.181,
+      "eval_steps_per_second": 1.09,
+      "step": 1670
+    },
+    {
+      "epoch": 2.395653802922443,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.0019040767386091127,
+      "loss": 2.8169,
+      "step": 2000
+    },
+    {
+      "epoch": 2.9951292618958414,
+      "grad_norm": 0.03466796875,
+      "learning_rate": 0.001880095923261391,
+      "loss": 2.833,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.562298774719238,
+      "eval_runtime": 920.2844,
+      "eval_samples_per_second": 2.173,
+      "eval_steps_per_second": 1.087,
+      "step": 2505
+    },
+    {
+      "epoch": 3.5934807043836643,
+      "grad_norm": 0.028564453125,
+      "learning_rate": 0.001856115107913669,
+      "loss": 2.771,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.493237495422363,
+      "eval_runtime": 921.4924,
+      "eval_samples_per_second": 2.17,
+      "eval_steps_per_second": 1.085,
+      "step": 3340
+    },
+    {
+      "epoch": 4.191832146871487,
+      "grad_norm": 0.0264892578125,
+      "learning_rate": 0.0018321342925659472,
+      "loss": 2.7542,
+      "step": 3500
+    },
+    {
+      "epoch": 4.791307605844886,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 0.0018081534772182255,
+      "loss": 2.7381,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.453831195831299,
+      "eval_runtime": 920.053,
+      "eval_samples_per_second": 2.174,
+      "eval_steps_per_second": 1.087,
+      "step": 4175
+    },
+    {
+      "epoch": 5.3896590483327085,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 0.0017841726618705036,
+      "loss": 2.7223,
+      "step": 4500
+    },
+    {
+      "epoch": 5.989134507306107,
+      "grad_norm": 0.04248046875,
+      "learning_rate": 0.0017601918465227817,
+      "loss": 2.7145,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 5.4245195388793945,
+      "eval_runtime": 917.9041,
+      "eval_samples_per_second": 2.179,
+      "eval_steps_per_second": 1.089,
+      "step": 5010
+    },
+    {
+      "epoch": 6.587485949793931,
+      "grad_norm": 0.0419921875,
+      "learning_rate": 0.00173621103117506,
+      "loss": 2.6994,
+      "step": 5500
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 5.405287742614746,
+      "eval_runtime": 961.0685,
+      "eval_samples_per_second": 2.081,
+      "eval_steps_per_second": 1.041,
+      "step": 5845
+    },
+    {
+      "epoch": 7.185837392281753,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 0.0017122302158273381,
+      "loss": 2.6968,
+      "step": 6000
+    },
+    {
+      "epoch": 7.785312851255152,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.0016882494004796162,
+      "loss": 2.6904,
+      "step": 6500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 5.388819217681885,
+      "eval_runtime": 907.4823,
+      "eval_samples_per_second": 2.204,
+      "eval_steps_per_second": 1.102,
+      "step": 6680
+    },
+    {
+      "epoch": 8.383664293742974,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 0.0016642685851318945,
+      "loss": 2.6778,
+      "step": 7000
+    },
+    {
+      "epoch": 8.983139752716372,
+      "grad_norm": 0.035888671875,
+      "learning_rate": 0.0016402877697841726,
+      "loss": 2.68,
+      "step": 7500
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 5.374368667602539,
+      "eval_runtime": 907.3526,
+      "eval_samples_per_second": 2.204,
+      "eval_steps_per_second": 1.102,
+      "step": 7515
+    },
+    {
+      "epoch": 18.999925065567627,
+      "eval_loss": 5.311040878295898,
+      "eval_runtime": 917.7051,
+      "eval_samples_per_second": 2.179,
+      "eval_steps_per_second": 1.09,
+      "step": 7923
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.6443868505824246e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ea8c713dc1b5b8cc0c8564f4de0eac0d059af29e1647cad9759dcf991216dd
+size 5304