Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37537bebcee751fd219bd12710e7f6fc35e7a2bcd9de163f31efd20109f6b6b2
+oid sha256:40145ecff317bd1f6c69b62983e0711046541ab7d790bdb86d528639e5541f1d
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c77566c9e235fb2ed777b4056307f8879ad18756045b0f3aab66d566376200
+oid sha256:dff68b2babb14bc5310faa75da1034e23265149a2d6fef15dd9f08200d0a42b7
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e0a757ffe6c9fcd3b1bf3120b902f92c3aa5d6542e79c5ea824ded072ba2b1f
+oid sha256:aa0de0c32bf94efe74fce56eafc87e41e69cc5016d5c33867cf1c8934b8875ce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:317ba05605195c1d4e2040522f74e7ab98f17d7a309d9ff3aaeabe58a301e214
+oid sha256:c9abf3b00130ebbc35657fb7788755e92886d9a53e2a5677dea2a31074b05473
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2168477773666382,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.10474860335195531,
+  "best_metric": 1.1949564218521118,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.13966480446927373,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 11.438,
       "eval_steps_per_second": 2.864,
       "step": 150
+    },
+    {
+      "epoch": 0.11173184357541899,
+      "grad_norm": 0.4937569499015808,
+      "learning_rate": 0.00018053067903555837,
+      "loss": 0.9268,
+      "step": 160
+    },
+    {
+      "epoch": 0.11871508379888268,
+      "grad_norm": 0.45097047090530396,
+      "learning_rate": 0.00017525871366768012,
+      "loss": 0.8534,
+      "step": 170
+    },
+    {
+      "epoch": 0.12569832402234637,
+      "grad_norm": 0.442699670791626,
+      "learning_rate": 0.00016964445490919413,
+      "loss": 0.8584,
+      "step": 180
+    },
+    {
+      "epoch": 0.13268156424581007,
+      "grad_norm": 0.49953675270080566,
+      "learning_rate": 0.00016371525486442843,
+      "loss": 0.7786,
+      "step": 190
+    },
+    {
+      "epoch": 0.13966480446927373,
+      "grad_norm": 1.2703161239624023,
+      "learning_rate": 0.0001575,
+      "loss": 1.9828,
+      "step": 200
+    },
+    {
+      "epoch": 0.13966480446927373,
+      "eval_loss": 1.1949564218521118,
+      "eval_runtime": 51.9478,
+      "eval_samples_per_second": 11.608,
+      "eval_steps_per_second": 2.907,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.212345230327808e+16,
+  "total_flos": 5.652007524237312e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null