Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63511d44cdc914119f5c885f1c739e0023041a9ad236fc9a57f6ff9c0333eb16
+oid sha256:1baae103d1a70751ff69c02cc46a9f4d5694aef2b2ad716816e9ce369bf13cf9
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd67f665ee333d5cacfa0b6159c217e72831fae2f2d447f9381dc2659128ce4
+oid sha256:a0295d7b4f32dfc4c3e9e4e375651affb1d5aa30373d504601c58c6596653c30
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3395cc0c92099e3a41f5095fd540270dd8b496efba101003c928717ffc8eedfe
+oid sha256:1150f380110405e1bed53cc98e2dc5152739fc9b386bc9c1b097f497bb96f5d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5cdfe5ed4f14bdadfee62402701e9c3c91a7e1b8246c7c7f0be536b67574fb3
+oid sha256:797161cb36b8434a2e9b424b1551b1d663e1ac4112ca3f634c3c132aead6996b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4066200256347656,
   "best_model_checkpoint": "mikhail_panzo/fil_b32_le4_s8000/checkpoint-5500",
-  "epoch": 164.83516483516485,
+  "epoch": 175.82417582417582,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1177,6 +1177,84 @@
       "eval_samples_per_second": 13.08,
       "eval_steps_per_second": 1.706,
       "step": 7500
+    },
+    {
+      "epoch": 165.93406593406593,
+      "grad_norm": 1.1622841358184814,
+      "learning_rate": 7.55e-06,
+      "loss": 0.3542,
+      "step": 7550
+    },
+    {
+      "epoch": 167.03296703296704,
+      "grad_norm": 0.767804741859436,
+      "learning_rate": 6.716666666666667e-06,
+      "loss": 0.3516,
+      "step": 7600
+    },
+    {
+      "epoch": 168.13186813186815,
+      "grad_norm": 0.7939496636390686,
+      "learning_rate": 5.8833333333333335e-06,
+      "loss": 0.3516,
+      "step": 7650
+    },
+    {
+      "epoch": 169.23076923076923,
+      "grad_norm": 0.826722264289856,
+      "learning_rate": 5.050000000000001e-06,
+      "loss": 0.3536,
+      "step": 7700
+    },
+    {
+      "epoch": 170.32967032967034,
+      "grad_norm": 1.0055506229400635,
+      "learning_rate": 4.216666666666666e-06,
+      "loss": 0.3515,
+      "step": 7750
+    },
+    {
+      "epoch": 171.42857142857142,
+      "grad_norm": 0.9588921070098877,
+      "learning_rate": 3.3833333333333337e-06,
+      "loss": 0.3501,
+      "step": 7800
+    },
+    {
+      "epoch": 172.52747252747253,
+      "grad_norm": 0.7313802242279053,
+      "learning_rate": 2.55e-06,
+      "loss": 0.353,
+      "step": 7850
+    },
+    {
+      "epoch": 173.62637362637363,
+      "grad_norm": 0.7923821210861206,
+      "learning_rate": 1.7166666666666668e-06,
+      "loss": 0.3526,
+      "step": 7900
+    },
+    {
+      "epoch": 174.72527472527472,
+      "grad_norm": 0.7615464329719543,
+      "learning_rate": 8.833333333333334e-07,
+      "loss": 0.3473,
+      "step": 7950
+    },
+    {
+      "epoch": 175.82417582417582,
+      "grad_norm": 0.6758411526679993,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 0.3461,
+      "step": 8000
+    },
+    {
+      "epoch": 175.82417582417582,
+      "eval_loss": 0.40872836112976074,
+      "eval_runtime": 13.3243,
+      "eval_samples_per_second": 12.083,
+      "eval_steps_per_second": 1.576,
+      "step": 8000
     }
   ],
   "logging_steps": 50,
@@ -1191,12 +1269,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.446529244284723e+16,
+  "total_flos": 4.743072546477725e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null