Training in progress, step 1000, checkpoint

last-checkpoint/adapter_config.json

@@ -25,12 +25,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "down_proj",
-    "gate_proj",
     "k_proj",
-    "v_proj",
+    "down_proj",
+    "o_proj",
     "q_proj",
-    "o_proj"
+    "v_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f06a94a8fd2110630b29f1a0fd61ece5d491e081468de01dce6bcb49a29196b3
+oid sha256:85928d986f2cd15fb887ee4e40bc18ea50570b9cc2b7c36dae87cce33f1f15c9
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:583aa4e7918fb15bddf477cd5bcb1d9cae4199ecc8a16903e5bbd6fb6f6c04a5
+oid sha256:55fc203eded4895da87380bd227f3349d9e16d83a889d7bd948c3d71d682fccf
 size 591203178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
+oid sha256:7682299c566684ea51cf26f0c86b6ffaa3c0bc63cbdf84674b29a2c62ac72143
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:822082b213c0642410a7baeaf5135c14aa4c940d0ddb23409fe69b75772aee28
+oid sha256:3c46d5bba25f025149448ec23ffcd8a74fcd8ccfdf129227c5a3d660bb3b1333
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6491499227202473,
+  "epoch": 2.061823802163833,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -632,6 +632,162 @@
       "eval_samples_per_second": 0.409,
       "eval_steps_per_second": 0.409,
       "step": 800
+    },
+    {
+      "epoch": 1.6697578567748583,
+      "grad_norm": 0.4012995660305023,
+      "learning_rate": 4.898007313042975e-05,
+      "loss": 0.1359,
+      "step": 810
+    },
+    {
+      "epoch": 1.6903657908294694,
+      "grad_norm": 0.4577192962169647,
+      "learning_rate": 4.7780734517504985e-05,
+      "loss": 0.1306,
+      "step": 820
+    },
+    {
+      "epoch": 1.7109737248840804,
+      "grad_norm": 0.5553697943687439,
+      "learning_rate": 4.658267413416326e-05,
+      "loss": 0.1414,
+      "step": 830
+    },
+    {
+      "epoch": 1.7315816589386914,
+      "grad_norm": 0.5764682292938232,
+      "learning_rate": 4.5386582026834906e-05,
+      "loss": 0.1407,
+      "step": 840
+    },
+    {
+      "epoch": 1.7521895929933025,
+      "grad_norm": 0.4649393558502197,
+      "learning_rate": 4.4193147108283016e-05,
+      "loss": 0.1291,
+      "step": 850
+    },
+    {
+      "epoch": 1.7727975270479135,
+      "grad_norm": 0.6201866865158081,
+      "learning_rate": 4.300305676081057e-05,
+      "loss": 0.1434,
+      "step": 860
+    },
+    {
+      "epoch": 1.7934054611025245,
+      "grad_norm": 0.6112945079803467,
+      "learning_rate": 4.1816996440349104e-05,
+      "loss": 0.1295,
+      "step": 870
+    },
+    {
+      "epoch": 1.8140133951571356,
+      "grad_norm": 0.4921644330024719,
+      "learning_rate": 4.063564928165682e-05,
+      "loss": 0.1325,
+      "step": 880
+    },
+    {
+      "epoch": 1.8346213292117466,
+      "grad_norm": 0.665326714515686,
+      "learning_rate": 3.9459695704853836e-05,
+      "loss": 0.164,
+      "step": 890
+    },
+    {
+      "epoch": 1.8552292632663576,
+      "grad_norm": 0.5689858198165894,
+      "learning_rate": 3.828981302352065e-05,
+      "loss": 0.147,
+      "step": 900
+    },
+    {
+      "epoch": 1.8552292632663576,
+      "eval_loss": 0.1883440464735031,
+      "eval_runtime": 149.5929,
+      "eval_samples_per_second": 0.401,
+      "eval_steps_per_second": 0.401,
+      "step": 900
+    },
+    {
+      "epoch": 1.8758371973209687,
+      "grad_norm": 0.5504728555679321,
+      "learning_rate": 3.712667505458622e-05,
+      "loss": 0.1228,
+      "step": 910
+    },
+    {
+      "epoch": 1.8964451313755797,
+      "grad_norm": 0.8000712990760803,
+      "learning_rate": 3.5970951730229785e-05,
+      "loss": 0.135,
+      "step": 920
+    },
+    {
+      "epoch": 1.9170530654301907,
+      "grad_norm": 0.4071889817714691,
+      "learning_rate": 3.482330871202029e-05,
+      "loss": 0.1197,
+      "step": 930
+    },
+    {
+      "epoch": 1.9376609994848017,
+      "grad_norm": 0.46653851866722107,
+      "learning_rate": 3.3684407007515484e-05,
+      "loss": 0.1395,
+      "step": 940
+    },
+    {
+      "epoch": 1.9582689335394128,
+      "grad_norm": 0.6100273132324219,
+      "learning_rate": 3.255490258954167e-05,
+      "loss": 0.1347,
+      "step": 950
+    },
+    {
+      "epoch": 1.9788768675940238,
+      "grad_norm": 0.5089631080627441,
+      "learning_rate": 3.14354460183732e-05,
+      "loss": 0.12,
+      "step": 960
+    },
+    {
+      "epoch": 1.9994848016486348,
+      "grad_norm": 0.4348441958427429,
+      "learning_rate": 3.032668206702959e-05,
+      "loss": 0.1289,
+      "step": 970
+    },
+    {
+      "epoch": 2.020607934054611,
+      "grad_norm": 0.3667771816253662,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0908,
+      "step": 980
+    },
+    {
+      "epoch": 2.041215868109222,
+      "grad_norm": 0.420012891292572,
+      "learning_rate": 2.8143779954949267e-05,
+      "loss": 0.0718,
+      "step": 990
+    },
+    {
+      "epoch": 2.061823802163833,
+      "grad_norm": 0.3521002233028412,
+      "learning_rate": 2.70708990795975e-05,
+      "loss": 0.0668,
+      "step": 1000
+    },
+    {
+      "epoch": 2.061823802163833,
+      "eval_loss": 0.1961071491241455,
+      "eval_runtime": 149.4232,
+      "eval_samples_per_second": 0.402,
+      "eval_steps_per_second": 0.402,
+      "step": 1000
     }
   ],
   "logging_steps": 10,
@@ -651,7 +807,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.309328094007296e+16,
+  "total_flos": 5.394040116523008e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a137e88e0e55a17fda65e854b20c699b62b6ccacbdb5fb18d98d0daf1f24b9f
+oid sha256:929586f453c837dd2c45da477cee81ff19a4b897cb7beb925285c835f78d9f3f
 size 5816