Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4630b10bcb703fa73c88566c65b8765ba833dfcbbccdcf2ceaa5e683a4421073
+oid sha256:318016cfc7986b72eb4bca4cfaddf78c33c84df79b9ac5651f552a82572a2c2c
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c2e87d1fd0e4803927f85e4bdc062f12323e17e2826feb55609cff3a3034902
+oid sha256:9e22d83112510bac4fff2a687d78576765f281510d114f79f4b49770357981a7
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b81b435f5b81d669a83487dc0b8421753e0811d3da78bc68ec4cced5eb3ce95
+oid sha256:d81a22f4738ee136fdf9bdad0f3d8a555dfbc12dc9c7cad1ae9b4a8017437a7b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.697222113609314,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.015479876160990712,
+  "best_metric": 1.517770528793335,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.030959752321981424,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 12.04,
       "eval_steps_per_second": 3.027,
       "step": 10
+    },
+    {
+      "epoch": 0.018575851393188854,
+      "grad_norm": 0.893426775932312,
+      "learning_rate": 0.000163742398974869,
+      "loss": 5.2009,
+      "step": 12
+    },
+    {
+      "epoch": 0.02321981424148607,
+      "grad_norm": 1.1135708093643188,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.5095,
+      "step": 15
+    },
+    {
+      "epoch": 0.02321981424148607,
+      "eval_loss": 1.5802924633026123,
+      "eval_runtime": 44.6107,
+      "eval_samples_per_second": 12.217,
+      "eval_steps_per_second": 3.071,
+      "step": 15
+    },
+    {
+      "epoch": 0.02786377708978328,
+      "grad_norm": 1.0101398229599,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 5.7148,
+      "step": 18
+    },
+    {
+      "epoch": 0.030959752321981424,
+      "eval_loss": 1.517770528793335,
+      "eval_runtime": 44.9777,
+      "eval_samples_per_second": 12.117,
+      "eval_steps_per_second": 3.046,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1925729759461376e+16,
+  "total_flos": 1.8460376203001856e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null