Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa03262fa600c23c73eb38f630e6e37d2dd73d35d50fd6d27f57cb701c04ee3e
+oid sha256:1ed6f85fade85a976e1f7990a8865c43aad40178a93510347b7af112fbf2e4db
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a83344668591019b941a8c5a10e36baed03348b1bbb4a722d4f17f1bc56807be
+oid sha256:154349c6930605d21703f8c9cc83a7de0987054914778f92c9dd272fa18db35f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad58fdaa03f28f805ee798c1f4fa2fa8a03d2c96e0486e1083d7602c466108ac
+oid sha256:fdd0329478f47a184b29462935e0662302e2741cb4733c3e036d6c76c6e3ef1a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f9183784ee9ad5ed6f2b6aefaf4042415c400d41579aaf5e1c414e6e7662516
+oid sha256:184154556c3872ae49967ee666243c10926f4c0b40679baf7c033dde47a4ca79
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:883e1bd0a2ba454bb75896178fa173561c15a90a7123eb0b3b4ec3a729de500d
+oid sha256:dffaeeb43d1f2ab824f4ce049d55468a31cd73406cd447e928083d6f5f0f46d2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb1666c341fc2dde6f57ac7db2f0cb5caab46f026d3ca93ac102bad041f72c75
+oid sha256:b3d2b7830a2aca28894c43725acef094d8e1ee214439d3cb61749b68c14f2609
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
+oid sha256:1fd9769bcb04586b7ead175b588f12a0bbbeba72d5f308b868ba8f36b77aa801
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.40124958753585815,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.3270645952575634,
+  "epoch": 0.41428182065958025,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,146 @@
       "eval_samples_per_second": 14.31,
       "eval_steps_per_second": 3.721,
       "step": 75
+    },
+    {
+      "epoch": 0.3314254565276642,
+      "grad_norm": 0.48104754090309143,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 0.6608,
+      "step": 76
+    },
+    {
+      "epoch": 0.3357863177977651,
+      "grad_norm": 0.43779367208480835,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 0.4484,
+      "step": 77
+    },
+    {
+      "epoch": 0.3401471790678659,
+      "grad_norm": 0.4079342186450958,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 0.4617,
+      "step": 78
+    },
+    {
+      "epoch": 0.3445080403379667,
+      "grad_norm": 0.4270339012145996,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 0.4245,
+      "step": 79
+    },
+    {
+      "epoch": 0.3488689016080676,
+      "grad_norm": 0.4463932514190674,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 0.3953,
+      "step": 80
+    },
+    {
+      "epoch": 0.35322976287816843,
+      "grad_norm": 0.4444558024406433,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 0.3951,
+      "step": 81
+    },
+    {
+      "epoch": 0.3575906241482693,
+      "grad_norm": 0.4303630590438843,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 0.4199,
+      "step": 82
+    },
+    {
+      "epoch": 0.36195148541837013,
+      "grad_norm": 0.4083124101161957,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 0.3978,
+      "step": 83
+    },
+    {
+      "epoch": 0.36631234668847096,
+      "grad_norm": 0.41896235942840576,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 0.3749,
+      "step": 84
+    },
+    {
+      "epoch": 0.37067320795857184,
+      "grad_norm": 0.44455498456954956,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 0.3634,
+      "step": 85
+    },
+    {
+      "epoch": 0.37503406922867266,
+      "grad_norm": 0.46264758706092834,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 0.3572,
+      "step": 86
+    },
+    {
+      "epoch": 0.3793949304987735,
+      "grad_norm": 0.5216580629348755,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 0.3992,
+      "step": 87
+    },
+    {
+      "epoch": 0.38375579176887437,
+      "grad_norm": 0.48434847593307495,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 0.6502,
+      "step": 88
+    },
+    {
+      "epoch": 0.3881166530389752,
+      "grad_norm": 0.50812166929245,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 0.4916,
+      "step": 89
+    },
+    {
+      "epoch": 0.39247751430907607,
+      "grad_norm": 0.4391539692878723,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 0.4395,
+      "step": 90
+    },
+    {
+      "epoch": 0.3968383755791769,
+      "grad_norm": 0.3883734345436096,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 0.3915,
+      "step": 91
+    },
+    {
+      "epoch": 0.4011992368492777,
+      "grad_norm": 0.39511629939079285,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 0.3902,
+      "step": 92
+    },
+    {
+      "epoch": 0.4055600981193786,
+      "grad_norm": 0.3681911528110504,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 0.3975,
+      "step": 93
+    },
+    {
+      "epoch": 0.4099209593894794,
+      "grad_norm": 0.40158364176750183,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 0.378,
+      "step": 94
+    },
+    {
+      "epoch": 0.41428182065958025,
+      "grad_norm": 0.41014018654823303,
+      "learning_rate": 1e-05,
+      "loss": 0.3961,
+      "step": 95
     }
   ],
   "logging_steps": 1,
@@ -587,12 +727,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.952125425975296e+17,
+  "total_flos": 1.1339358872902042e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null