Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:371d8b9a6fe635a909de47a0c4b85a48069f0c7be7fdc3b532a16b7d3ce033df
+oid sha256:d54b6d841a305b1348584f5a5a318f847f70677929ed7b0f41b13f073813d5d3
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:514d4bceaf94b4325410c2c05d4c07f955ee2baa03f53e4c283477d55192f206
+oid sha256:31d98f20cb75f1d52b92765df2e8883336dd1699cdf8befe1d42ff436795fd69
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7fc2d18456a9dba9f0b80852db8a64c696effa2f9d86b32cb6984d1901477d7
+oid sha256:4615fa5a102f05823341d82bbf0b23b71ae0cc83ff74ce30a5e10dea97fd8208
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9d3305ea9d2a6a96a857dfcbc335cdacc622dca1e2363957a78331479550c8
+oid sha256:5ebe9ac0b88e6f1ca5d647eb6ccb8e34dd0b5db747679442ede1aeae67c9b73f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aae6717f08b8cd7f35b932194ec7617e13c784c4a0c93aac482beb64fe27b4c
+oid sha256:a070df3bf6f3a70672b417cede8d1503c6308ccd2611d3a93d5e84db32fd82d9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f7075dbc239ef2c0522af8392d3bb10349f689f330f096293a8e4b47675b69e
+oid sha256:368d55328374d207110dc268685fdc0b707984137ce720a9e9f7580135a36500
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 5.733458042144775,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03707136237256719,
+  "best_metric": 5.243720531463623,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07414272474513438,
   "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": 14.399,
       "eval_steps_per_second": 3.744,
       "step": 25
+    },
+    {
+      "epoch": 0.03855421686746988,
+      "grad_norm": 14.637948989868164,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 5.8067,
+      "step": 26
+    },
+    {
+      "epoch": 0.04003707136237257,
+      "grad_norm": 13.025384902954102,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 5.6793,
+      "step": 27
+    },
+    {
+      "epoch": 0.04151992585727526,
+      "grad_norm": 7.037714004516602,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 5.5536,
+      "step": 28
+    },
+    {
+      "epoch": 0.043002780352177944,
+      "grad_norm": 2.708852529525757,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 5.4214,
+      "step": 29
+    },
+    {
+      "epoch": 0.04448563484708063,
+      "grad_norm": 1.5370925664901733,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 5.3473,
+      "step": 30
+    },
+    {
+      "epoch": 0.04596848934198332,
+      "grad_norm": 1.4543185234069824,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 5.3576,
+      "step": 31
+    },
+    {
+      "epoch": 0.047451343836886005,
+      "grad_norm": 1.3065513372421265,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 5.3533,
+      "step": 32
+    },
+    {
+      "epoch": 0.04893419833178869,
+      "grad_norm": 1.3391211032867432,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 5.3029,
+      "step": 33
+    },
+    {
+      "epoch": 0.05041705282669138,
+      "grad_norm": 1.0643391609191895,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 5.301,
+      "step": 34
+    },
+    {
+      "epoch": 0.051899907321594066,
+      "grad_norm": 1.066335916519165,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 5.3114,
+      "step": 35
+    },
+    {
+      "epoch": 0.05338276181649675,
+      "grad_norm": 1.191772222518921,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 5.2993,
+      "step": 36
+    },
+    {
+      "epoch": 0.05486561631139945,
+      "grad_norm": 1.4020297527313232,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 5.3416,
+      "step": 37
+    },
+    {
+      "epoch": 0.056348470806302134,
+      "grad_norm": 0.9556575417518616,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 5.2409,
+      "step": 38
+    },
+    {
+      "epoch": 0.05783132530120482,
+      "grad_norm": 1.0040682554244995,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 5.2272,
+      "step": 39
+    },
+    {
+      "epoch": 0.05931417979610751,
+      "grad_norm": 0.9176912903785706,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 5.1909,
+      "step": 40
+    },
+    {
+      "epoch": 0.060797034291010195,
+      "grad_norm": 0.7513061165809631,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 5.2537,
+      "step": 41
+    },
+    {
+      "epoch": 0.06227988878591288,
+      "grad_norm": 0.6128130555152893,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 5.252,
+      "step": 42
+    },
+    {
+      "epoch": 0.06376274328081558,
+      "grad_norm": 0.566775381565094,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 5.2356,
+      "step": 43
+    },
+    {
+      "epoch": 0.06524559777571826,
+      "grad_norm": 0.49181070923805237,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 5.2679,
+      "step": 44
+    },
+    {
+      "epoch": 0.06672845227062095,
+      "grad_norm": 0.5992257595062256,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 5.227,
+      "step": 45
+    },
+    {
+      "epoch": 0.06821130676552363,
+      "grad_norm": 1.2758322954177856,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 5.2075,
+      "step": 46
+    },
+    {
+      "epoch": 0.06969416126042632,
+      "grad_norm": 0.846122145652771,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 5.286,
+      "step": 47
+    },
+    {
+      "epoch": 0.071177015755329,
+      "grad_norm": 1.0701982975006104,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 5.2788,
+      "step": 48
+    },
+    {
+      "epoch": 0.0726598702502317,
+      "grad_norm": 1.3257886171340942,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 5.2388,
+      "step": 49
+    },
+    {
+      "epoch": 0.07414272474513438,
+      "grad_norm": 2.1276042461395264,
+      "learning_rate": 1e-05,
+      "loss": 5.3273,
+      "step": 50
+    },
+    {
+      "epoch": 0.07414272474513438,
+      "eval_loss": 5.243720531463623,
+      "eval_runtime": 3.4628,
+      "eval_samples_per_second": 14.439,
+      "eval_steps_per_second": 3.754,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null