Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c31252227a6af7a6e65f9d45c7494011d167c4f702a14da71d94d44964bd947f
+oid sha256:9e2446240d353c1f64cd3e199db9012e63178e7af9c88c8e7b4eb27f0e98311f
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b25f7b58da1e29481438dbf5ec2bbbeda853a96efc7ef790748a1310fd658d
+oid sha256:e4b86cf7e073f97eabad82028f7649b86b9c8f16c4ae8ca878f05af20e6145f9
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b32667b227f6275884c5848fe8070c6219d70bf14c4e440c0b1b379a04dba2
+oid sha256:17e33bc2ae45877b03713d1b54e9f0e817e6bd75f767e38ef69da10a08dd2c60
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0873218b672c06f65bcbdbef35d38ce732851774107c53582718a1316dbb1e40
+oid sha256:cd7cf500208b0b7f84d388a948be38cab3fa49ec9e5ed4521e775b2c1f3ef453
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.38211727142333984,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.08869179600886919,
+  "best_metric": 0.31679707765579224,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.13303769401330376,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 12.441,
       "eval_steps_per_second": 3.117,
       "step": 100
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 0.8537772297859192,
+      "learning_rate": 0.00019231131849308138,
+      "loss": 0.3774,
+      "step": 110
+    },
+    {
+      "epoch": 0.10643015521064302,
+      "grad_norm": 2.790709972381592,
+      "learning_rate": 0.00018923623308232218,
+      "loss": 0.3956,
+      "step": 120
+    },
+    {
+      "epoch": 0.11529933481152993,
+      "grad_norm": 1.3601632118225098,
+      "learning_rate": 0.00018572883366372081,
+      "loss": 0.4427,
+      "step": 130
+    },
+    {
+      "epoch": 0.12416851441241686,
+      "grad_norm": 1.0446776151657104,
+      "learning_rate": 0.00018180620793468224,
+      "loss": 0.2675,
+      "step": 140
+    },
+    {
+      "epoch": 0.13303769401330376,
+      "grad_norm": 2.1166090965270996,
+      "learning_rate": 0.00017748746653345728,
+      "loss": 0.2237,
+      "step": 150
+    },
+    {
+      "epoch": 0.13303769401330376,
+      "eval_loss": 0.31679707765579224,
+      "eval_runtime": 38.1684,
+      "eval_samples_per_second": 12.445,
+      "eval_steps_per_second": 3.118,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5247139659513856e+16,
+  "total_flos": 3.77448931786752e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null