Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318016cfc7986b72eb4bca4cfaddf78c33c84df79b9ac5651f552a82572a2c2c
+oid sha256:c8453b454307224010b2cc85fe903009275e6000335919a2ac770de3ecb12e66
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e22d83112510bac4fff2a687d78576765f281510d114f79f4b49770357981a7
+oid sha256:0de7bae7379aef61834e9b071c5f2492759fd9a9c65d94d009502ba4db1e8180
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81a22f4738ee136fdf9bdad0f3d8a555dfbc12dc9c7cad1ae9b4a8017437a7b
+oid sha256:fc799bd1a0024a0414e6ce57cc9e82527ce640d3d10a069ceab3ef79e5c6d8a1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.517770528793335,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.030959752321981424,
+  "best_metric": 1.5052969455718994,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.04643962848297214,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 12.117,
       "eval_steps_per_second": 3.046,
       "step": 20
+    },
+    {
+      "epoch": 0.032507739938080496,
+      "grad_norm": 0.9914897084236145,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 7.9927,
+      "step": 21
+    },
+    {
+      "epoch": 0.03715170278637771,
+      "grad_norm": 1.004940152168274,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 8.3128,
+      "step": 24
+    },
+    {
+      "epoch": 0.03869969040247678,
+      "eval_loss": 1.511370062828064,
+      "eval_runtime": 45.2973,
+      "eval_samples_per_second": 12.032,
+      "eval_steps_per_second": 3.024,
+      "step": 25
+    },
+    {
+      "epoch": 0.04179566563467492,
+      "grad_norm": 1.2595340013504028,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 7.8773,
+      "step": 27
+    },
+    {
+      "epoch": 0.04643962848297214,
+      "grad_norm": 1.1866806745529175,
+      "learning_rate": 0.0,
+      "loss": 8.7072,
+      "step": 30
+    },
+    {
+      "epoch": 0.04643962848297214,
+      "eval_loss": 1.5052969455718994,
+      "eval_runtime": 45.3007,
+      "eval_samples_per_second": 12.031,
+      "eval_steps_per_second": 3.024,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.8460376203001856e+16,
+  "total_flos": 2.4995022646542336e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null