Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:756844225b672b546ebfe704101006279a399be2651596f230282541528d88c8
+oid sha256:f313f73f7d54420336429c26e619d0ff3834e89caa14732ea1305cf8745b841c
 size 6063056

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:376f716bed502190c55693296c4e98dea40e264d6706907ef8236d896008a8ae
+oid sha256:bbbb306acdd8817282f3cd37e4c7c1019be776585cab09147784248b7d6daa40
 size 12149579

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc8c6913278f9c517962f5aa36e8b395dff7d28049918ddd24f3bbc58af2ae5
+oid sha256:b90bfb5f2441495d488f850d8a7176fd410083adef90c2055b29a882b0284af0
 size 14455

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:708fd45745992b5a5ef9a8681fe5c4df9b6010cdc6950ef55aec62e5d0c66fd2
+oid sha256:77ced95f1c67747bc54b27b1781254392fe5947e21557e2368922a37a0b7cc5f
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 1.0,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -86,6 +86,84 @@
       "eval_samples_per_second": 39.285,
       "eval_steps_per_second": 4.911,
       "step": 100
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.4246294498443604,
+      "learning_rate": 0.00014072164948453607,
+      "loss": 3.777085876464844,
+      "step": 110
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.2241950035095215,
+      "learning_rate": 0.00012525773195876287,
+      "loss": 3.578862762451172,
+      "step": 120
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 2.186573028564453,
+      "learning_rate": 0.00010979381443298967,
+      "loss": 3.4002994537353515,
+      "step": 130
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.2067198753356934,
+      "learning_rate": 9.432989690721649e-05,
+      "loss": 3.246867370605469,
+      "step": 140
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.9926505088806152,
+      "learning_rate": 7.886597938144329e-05,
+      "loss": 3.099070739746094,
+      "step": 150
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.9743366241455078,
+      "learning_rate": 6.34020618556701e-05,
+      "loss": 3.0069753646850588,
+      "step": 160
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.9023700952529907,
+      "learning_rate": 4.79381443298969e-05,
+      "loss": 2.9152482986450194,
+      "step": 170
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.9220083951950073,
+      "learning_rate": 3.247422680412371e-05,
+      "loss": 2.8356719970703126,
+      "step": 180
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.8265043497085571,
+      "learning_rate": 1.7010309278350514e-05,
+      "loss": 2.830997657775879,
+      "step": 190
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9334819316864014,
+      "learning_rate": 1.5463917525773195e-06,
+      "loss": 2.792418098449707,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.788900852203369,
+      "eval_runtime": 25.3093,
+      "eval_samples_per_second": 39.511,
+      "eval_steps_per_second": 4.939,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -100,12 +178,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1104877559808.0,
+  "total_flos": 2210085808128.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null