Training in progress, step 1625, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee4e2d84e38cb73fc215ea160b72d8c65fb8ef814b9ce18e21001c4fceb2971e
+oid sha256:2235952bcc8cb41758f7b984fe58dd654193b0b7df69b358dea989152d0f6278
 size 410636248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5189682206216f1eb6c749f032237c2b81ba6a5a04045dadba360a7ff157fd
+oid sha256:34c529f4a84229c3ae46dce2f3e5222e610cf9eae06334adfd54155d57792572
 size 821393658

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70171b5cf4c5d65f8d1801780619a5ef6eaa49858f51f2d188c1b4ae2878778d
+oid sha256:9fc3183918ae68b4e8a620d193012eab94fc760f0b8667287157217a5c88f2d3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0db746135b039e0910ffb0031dacdf1ae5245ec4309f44b2f467d1af6778d5b2
+oid sha256:52dbf015c0fbf1630a81175a221e8cc220f8e050930d561b1a00f55047f5328b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.20959021151065826,
   "best_model_checkpoint": "./results/checkpoint-640",
-  "epoch": 4.615384615384615,
+  "epoch": 5.0,
   "eval_steps": 20,
-  "global_step": 1500,
+  "global_step": 1625,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1207,6 +1207,102 @@
       "eval_samples_per_second": 33.928,
       "eval_steps_per_second": 8.595,
       "step": 1500
+    },
+    {
+      "epoch": 4.676923076923077,
+      "grad_norm": 0.007997775450348854,
+      "learning_rate": 1.2923076923076924e-06,
+      "loss": 0.1421,
+      "step": 1520
+    },
+    {
+      "epoch": 4.676923076923077,
+      "eval_accuracy": 0.9333333333333333,
+      "eval_loss": 0.400637149810791,
+      "eval_runtime": 4.3593,
+      "eval_samples_per_second": 34.41,
+      "eval_steps_per_second": 8.717,
+      "step": 1520
+    },
+    {
+      "epoch": 4.7384615384615385,
+      "grad_norm": 0.004181304015219212,
+      "learning_rate": 1.0461538461538463e-06,
+      "loss": 0.0002,
+      "step": 1540
+    },
+    {
+      "epoch": 4.7384615384615385,
+      "eval_accuracy": 0.9266666666666666,
+      "eval_loss": 0.40295225381851196,
+      "eval_runtime": 4.5588,
+      "eval_samples_per_second": 32.903,
+      "eval_steps_per_second": 8.336,
+      "step": 1540
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.003899338422343135,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 0.0002,
+      "step": 1560
+    },
+    {
+      "epoch": 4.8,
+      "eval_accuracy": 0.9266666666666666,
+      "eval_loss": 0.4034216105937958,
+      "eval_runtime": 4.6347,
+      "eval_samples_per_second": 32.365,
+      "eval_steps_per_second": 8.199,
+      "step": 1560
+    },
+    {
+      "epoch": 4.861538461538462,
+      "grad_norm": 0.004380157217383385,
+      "learning_rate": 5.53846153846154e-07,
+      "loss": 0.0628,
+      "step": 1580
+    },
+    {
+      "epoch": 4.861538461538462,
+      "eval_accuracy": 0.9333333333333333,
+      "eval_loss": 0.38764962553977966,
+      "eval_runtime": 4.5609,
+      "eval_samples_per_second": 32.888,
+      "eval_steps_per_second": 8.332,
+      "step": 1580
+    },
+    {
+      "epoch": 4.923076923076923,
+      "grad_norm": 0.004398785065859556,
+      "learning_rate": 3.0769230769230774e-07,
+      "loss": 0.0003,
+      "step": 1600
+    },
+    {
+      "epoch": 4.923076923076923,
+      "eval_accuracy": 0.9333333333333333,
+      "eval_loss": 0.38795334100723267,
+      "eval_runtime": 4.4706,
+      "eval_samples_per_second": 33.553,
+      "eval_steps_per_second": 8.5,
+      "step": 1600
+    },
+    {
+      "epoch": 4.984615384615385,
+      "grad_norm": 0.0024876066017895937,
+      "learning_rate": 6.153846153846154e-08,
+      "loss": 0.0003,
+      "step": 1620
+    },
+    {
+      "epoch": 4.984615384615385,
+      "eval_accuracy": 0.9333333333333333,
+      "eval_loss": 0.39026668667793274,
+      "eval_runtime": 4.3714,
+      "eval_samples_per_second": 34.314,
+      "eval_steps_per_second": 8.693,
+      "step": 1620
     }
   ],
   "logging_steps": 20,
@@ -1221,12 +1317,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1380510818592000.0,
+  "total_flos": 1494172738952400.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null