Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba02c01533c97c07e8182e793f898c557b23d253dd3ee2e63f35fc43eabba95
+oid sha256:88fb81e440d85a6605618a0971084cb49fe2a7e39a58f2bd580aea3401d0b6f8
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ff645f44dd408599245284ff2d40a6570958d266c63b910556c17d5d0869d6
+oid sha256:6a4ac9ea3ee5a462c9ceab4a9e4ae719693693e0cf78a6ec875aed88f35960ce
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddab19c27b913075780d33d64cc2ce42d82fa5dc5c18abe10939866a6353a7cd
+oid sha256:e936836b2cdc132491f556998ba2d3f8cb2dd14428b1b18cd5fae4ebbcb5a994
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f05a07b776abc173978a0e887e7c70d773d3b63ce9e1342d6d78880c1684ac0
+oid sha256:a760ba92960f08f363394eee4df1edc2c66e6b8b22489dbac9e6aa0f5ae478e1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.5439529418945312,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.01811922449719152,
+  "epoch": 0.03623844899438304,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 15.668,
       "eval_steps_per_second": 3.924,
       "step": 50
+    },
+    {
+      "epoch": 0.021743069396629823,
+      "grad_norm": 1.3696887493133545,
+      "learning_rate": 0.0002057490971767619,
+      "loss": 2.384,
+      "step": 60
+    },
+    {
+      "epoch": 0.02536691429606813,
+      "grad_norm": 1.702624797821045,
+      "learning_rate": 0.00020499761108038175,
+      "loss": 2.4112,
+      "step": 70
+    },
+    {
+      "epoch": 0.028990759195506432,
+      "grad_norm": 1.841941237449646,
+      "learning_rate": 0.00020374920287558198,
+      "loss": 2.3759,
+      "step": 80
+    },
+    {
+      "epoch": 0.03261460409494474,
+      "grad_norm": 2.737161874771118,
+      "learning_rate": 0.00020200995468164684,
+      "loss": 2.2692,
+      "step": 90
+    },
+    {
+      "epoch": 0.03623844899438304,
+      "grad_norm": 4.560957431793213,
+      "learning_rate": 0.00019978833994094855,
+      "loss": 2.1869,
+      "step": 100
+    },
+    {
+      "epoch": 0.03623844899438304,
+      "eval_loss": 2.719433307647705,
+      "eval_runtime": 74.2575,
+      "eval_samples_per_second": 15.648,
+      "eval_steps_per_second": 3.919,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -72,7 +115,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9711056163176448.0,
+  "total_flos": 1.932783022768128e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null