Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61b08b427524e889a0b8d382f9115eba3798ab208df96f84d67a1110d9c104b2
+oid sha256:ca27b7323d4f7628932290ac099ef40f94c68ff7c1e019417d6f64ef02ed8123
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d219537847fbd7111b0d0cd3e7da18b22435bb3ca07d6d17301098b460ef335
+oid sha256:744dbfefab11895284826e4e6fa4e87d7e7514a9e41fc6d8d3dec1633b5f79e7
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7fdad45a86febbfbf7416cb2067a77c42d668b5b524ad36010e05bf35427b6e
+oid sha256:ece47d351ec8541aeb5c36472c488dc667a04cd8f53d50bdc3cc307262d6739d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba9826396d1061aee6fdf7293fd789e47f8a5ac9db78d8396f43ecdcae9b12a2
+oid sha256:f11095f13a6bb8e73004d74d741982d584b499e9ac31a59ea1de9965f3fec76b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.40983906388282776,
   "best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-5500",
-  "epoch": 326.0869565217391,
+  "epoch": 347.82608695652175,
   "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": 23.069,
       "eval_steps_per_second": 2.902,
       "step": 7500
+    },
+    {
+      "epoch": 328.2608695652174,
+      "grad_norm": 0.8036932945251465,
+      "learning_rate": 7.566666666666667e-07,
+      "loss": 0.4167,
+      "step": 7550
+    },
+    {
+      "epoch": 330.4347826086956,
+      "grad_norm": 0.9011595845222473,
+      "learning_rate": 6.733333333333334e-07,
+      "loss": 0.4146,
+      "step": 7600
+    },
+    {
+      "epoch": 332.60869565217394,
+      "grad_norm": 1.1051392555236816,
+      "learning_rate": 5.900000000000001e-07,
+      "loss": 0.414,
+      "step": 7650
+    },
+    {
+      "epoch": 334.7826086956522,
+      "grad_norm": 0.8294230103492737,
+      "learning_rate": 5.066666666666667e-07,
+      "loss": 0.4136,
+      "step": 7700
+    },
+    {
+      "epoch": 336.95652173913044,
+      "grad_norm": 0.8385105729103088,
+      "learning_rate": 4.233333333333334e-07,
+      "loss": 0.4031,
+      "step": 7750
+    },
+    {
+      "epoch": 339.1304347826087,
+      "grad_norm": 1.015714406967163,
+      "learning_rate": 3.4000000000000003e-07,
+      "loss": 0.4013,
+      "step": 7800
+    },
+    {
+      "epoch": 341.30434782608694,
+      "grad_norm": 0.8815127611160278,
+      "learning_rate": 2.566666666666667e-07,
+      "loss": 0.4067,
+      "step": 7850
+    },
+    {
+      "epoch": 343.4782608695652,
+      "grad_norm": 1.0422344207763672,
+      "learning_rate": 1.7333333333333335e-07,
+      "loss": 0.4095,
+      "step": 7900
+    },
+    {
+      "epoch": 345.6521739130435,
+      "grad_norm": 1.6998138427734375,
+      "learning_rate": 9e-08,
+      "loss": 0.4089,
+      "step": 7950
+    },
+    {
+      "epoch": 347.82608695652175,
+      "grad_norm": 0.9665780067443848,
+      "learning_rate": 6.666666666666667e-09,
+      "loss": 0.4097,
+      "step": 8000
+    },
+    {
+      "epoch": 347.82608695652175,
+      "eval_loss": 0.41188350319862366,
+      "eval_runtime": 6.8472,
+      "eval_samples_per_second": 23.221,
+      "eval_steps_per_second": 2.921,
+      "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": 1.1135871544625309e+17,
+  "total_flos": 1.187693654068754e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null