Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207221a7ccafd9fb249443ff184dc37a386783b4913372479c3b49e98fa2f97c
+oid sha256:88fbd6c6f375e4cd472e7da2b752134a935cf6097a9691e329257e5cbce9e28c
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2478664d7b042df16d7224d903b96e42e49a4af119c6a67b89d8fb88c4c8e1
+oid sha256:3d6615828949cc0663b0abfc6e56152830c7d7f3401d9151979b8587e0364fc8
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb17a34161d58af6585cca69c4affc84a101b65e8e95b16133ade1f80628a37
+oid sha256:01c90d7440171073561ec2eb0828e445042549d385390b4d8e8050367b0edfef
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7b4ec0d2a6817e61aa0dcece64ccb5edeb51293ca750461a1d4986af8242f7
+oid sha256:d4aab6376e7fca731c9299f578de30183807e65cfa408cf9706e8d5e2242302e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f52e40c2b1cd00abc3a4f03c7a6b7f3120614f168db59fbfcabb2bfbfb3fbb
+oid sha256:8cf899700ef666beb62c0cba1f49c7a7fe22c536daa5e81a58deeccc24a7f087
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a2c54b9bdc33cf605e54fb5a9af2fb48a236f11634d473d9cff2f0b3ded9e8e
+oid sha256:7af7f363256dcfe8136244af9551305356130e281a4182575a6da40e28de61dc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.268705129623413,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.819672131147541,
+  "best_metric": 2.2637264728546143,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.6454918032786885,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 74.397,
       "eval_steps_per_second": 4.706,
       "step": 25
+    },
+    {
+      "epoch": 0.8524590163934426,
+      "grad_norm": 0.0991344079375267,
+      "learning_rate": 5e-05,
+      "loss": 2.3498,
+      "step": 26
+    },
+    {
+      "epoch": 0.8852459016393442,
+      "grad_norm": 0.12045133858919144,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.338,
+      "step": 27
+    },
+    {
+      "epoch": 0.9180327868852459,
+      "grad_norm": 0.13006040453910828,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.3029,
+      "step": 28
+    },
+    {
+      "epoch": 0.9508196721311475,
+      "grad_norm": 0.16934581100940704,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.2783,
+      "step": 29
+    },
+    {
+      "epoch": 0.9836065573770492,
+      "grad_norm": 0.3354940712451935,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.2464,
+      "step": 30
+    },
+    {
+      "epoch": 1.0225409836065573,
+      "grad_norm": 0.15646272897720337,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.9901,
+      "step": 31
+    },
+    {
+      "epoch": 1.055327868852459,
+      "grad_norm": 0.11801426857709885,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.1995,
+      "step": 32
+    },
+    {
+      "epoch": 1.0881147540983607,
+      "grad_norm": 0.14715805649757385,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.2941,
+      "step": 33
+    },
+    {
+      "epoch": 1.1209016393442623,
+      "grad_norm": 0.1737724095582962,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3553,
+      "step": 34
+    },
+    {
+      "epoch": 1.153688524590164,
+      "grad_norm": 0.19558919966220856,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.2409,
+      "step": 35
+    },
+    {
+      "epoch": 1.1864754098360657,
+      "grad_norm": 0.23931904137134552,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.3564,
+      "step": 36
+    },
+    {
+      "epoch": 1.2192622950819672,
+      "grad_norm": 0.3004460334777832,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.2929,
+      "step": 37
+    },
+    {
+      "epoch": 1.2520491803278688,
+      "grad_norm": 0.11587761342525482,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5015,
+      "step": 38
+    },
+    {
+      "epoch": 1.2848360655737705,
+      "grad_norm": 0.11674284189939499,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.0545,
+      "step": 39
+    },
+    {
+      "epoch": 1.3176229508196722,
+      "grad_norm": 0.13231879472732544,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.2792,
+      "step": 40
+    },
+    {
+      "epoch": 1.3504098360655736,
+      "grad_norm": 0.155413419008255,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.2946,
+      "step": 41
+    },
+    {
+      "epoch": 1.3831967213114753,
+      "grad_norm": 0.18727189302444458,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2622,
+      "step": 42
+    },
+    {
+      "epoch": 1.415983606557377,
+      "grad_norm": 0.2269286960363388,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.3557,
+      "step": 43
+    },
+    {
+      "epoch": 1.4487704918032787,
+      "grad_norm": 0.26384779810905457,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1776,
+      "step": 44
+    },
+    {
+      "epoch": 1.4815573770491803,
+      "grad_norm": 0.4085754454135895,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.4615,
+      "step": 45
+    },
+    {
+      "epoch": 1.514344262295082,
+      "grad_norm": 0.15077833831310272,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.1837,
+      "step": 46
+    },
+    {
+      "epoch": 1.5471311475409837,
+      "grad_norm": 0.11710967868566513,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.2568,
+      "step": 47
+    },
+    {
+      "epoch": 1.5799180327868854,
+      "grad_norm": 0.1437835991382599,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.3031,
+      "step": 48
+    },
+    {
+      "epoch": 1.612704918032787,
+      "grad_norm": 0.1696387678384781,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.272,
+      "step": 49
+    },
+    {
+      "epoch": 1.6454918032786885,
+      "grad_norm": 0.1985762119293213,
+      "learning_rate": 0.0,
+      "loss": 2.4134,
+      "step": 50
+    },
+    {
+      "epoch": 1.6454918032786885,
+      "eval_loss": 2.2637264728546143,
+      "eval_runtime": 5.5227,
+      "eval_samples_per_second": 74.42,
+      "eval_steps_per_second": 4.708,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1105265384842854e+17,
+  "total_flos": 2.210457704034468e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null