Training in progress, step 16568, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeeda4b1ee34efcb8cc9870b2c843e6649254ccabfeca77e86d631e6043a12c7
+oid sha256:d5aeb4ed25696f7e10e7543b90c5a47b6138a594baf57483d3c889f4f1c258f4
 size 150625560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad619e41a755fe598f7951c93afa49e976ac527f447e6a0b8b599bd265a02a63
+oid sha256:fe702f58a491cea98553ed6f74aecfeac0fa377b5678dc16b12b8bc2dfc14360
 size 602335994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8b7e7bf463c8aae6a90e1a089b32f412ca31160cb21f8d8c8b0ee26b9ca28d
+oid sha256:28e82f09e6e0a8d547118b1ff3e149779a831528016aa1b10eb3d2c1c802ac19
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab47855ede8e2538e1a83a739503d4b0055ccb1a5bd772cbc798bb06eb73f571
+oid sha256:0d3bb1f3bb0340b0b65b79ab24d36ed0f271ff49414747938c92ca607d666859
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.8620788508834134,
+  "epoch": 3.9992003259049143,
   "eval_steps": 500,
-  "global_step": 16000,
+  "global_step": 16568,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3496,11 +3496,130 @@
       "eval_steps_per_second": 20.463,
       "num_input_tokens_seen": 7729128049,
       "step": 16000
+    },
+    {
+      "epoch": 3.874149403262067,
+      "grad_norm": 0.26953125,
+      "learning_rate": 1.9541270559830995e-06,
+      "loss": 2.0974,
+      "mean_token_accuracy": 0.5552676925435662,
+      "num_input_tokens_seen": 7753351249,
+      "num_tokens": 3267712597.0,
+      "step": 16050
+    },
+    {
+      "epoch": 3.88621995564072,
+      "grad_norm": 0.27734375,
+      "learning_rate": 1.7655047532820282e-06,
+      "loss": 2.0956,
+      "mean_token_accuracy": 0.5543999705091118,
+      "num_input_tokens_seen": 7777499137,
+      "num_tokens": 3277902761.0,
+      "step": 16100
+    },
+    {
+      "epoch": 3.8982905080193735,
+      "grad_norm": 0.25,
+      "learning_rate": 1.576882450580957e-06,
+      "loss": 2.0949,
+      "mean_token_accuracy": 0.5548696434870363,
+      "num_input_tokens_seen": 7801633089,
+      "num_tokens": 3288082221.0,
+      "step": 16150
+    },
+    {
+      "epoch": 3.9103610603980266,
+      "grad_norm": 0.24609375,
+      "learning_rate": 1.3882601478798854e-06,
+      "loss": 2.0986,
+      "mean_token_accuracy": 0.5540741100907326,
+      "num_input_tokens_seen": 7825738481,
+      "num_tokens": 3298341216.0,
+      "step": 16200
+    },
+    {
+      "epoch": 3.9224316127766796,
+      "grad_norm": 0.263671875,
+      "learning_rate": 1.199637845178814e-06,
+      "loss": 2.0917,
+      "mean_token_accuracy": 0.556021711602807,
+      "num_input_tokens_seen": 7849877409,
+      "num_tokens": 3308431697.0,
+      "step": 16250
+    },
+    {
+      "epoch": 3.934502165155333,
+      "grad_norm": 0.255859375,
+      "learning_rate": 1.0110155424777427e-06,
+      "loss": 2.0983,
+      "mean_token_accuracy": 0.5542013296857476,
+      "num_input_tokens_seen": 7873955105,
+      "num_tokens": 3318516095.0,
+      "step": 16300
+    },
+    {
+      "epoch": 3.946572717533986,
+      "grad_norm": 0.2490234375,
+      "learning_rate": 8.223932397766712e-07,
+      "loss": 2.1049,
+      "mean_token_accuracy": 0.553213356398046,
+      "num_input_tokens_seen": 7898153793,
+      "num_tokens": 3328721862.0,
+      "step": 16350
+    },
+    {
+      "epoch": 3.9586432699126393,
+      "grad_norm": 0.2734375,
+      "learning_rate": 6.337709370755999e-07,
+      "loss": 2.0981,
+      "mean_token_accuracy": 0.5537924468889832,
+      "num_input_tokens_seen": 7922266993,
+      "num_tokens": 3338965333.0,
+      "step": 16400
+    },
+    {
+      "epoch": 3.9707138222912928,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 4.4514863437452844e-07,
+      "loss": 2.0952,
+      "mean_token_accuracy": 0.5555017331615091,
+      "num_input_tokens_seen": 7946376977,
+      "num_tokens": 3349129194.0,
+      "step": 16450
+    },
+    {
+      "epoch": 3.982784374669946,
+      "grad_norm": 0.279296875,
+      "learning_rate": 2.565263316734571e-07,
+      "loss": 2.0973,
+      "num_input_tokens_seen": 7970557393,
+      "step": 16500
+    },
+    {
+      "epoch": 3.982784374669946,
+      "eval_loss": 1.9680447578430176,
+      "eval_mean_token_accuracy": 0.5785172289325018,
+      "eval_num_tokens": 3359357384.0,
+      "eval_runtime": 131.3028,
+      "eval_samples_per_second": 81.582,
+      "eval_steps_per_second": 20.396,
+      "num_input_tokens_seen": 7970557393,
+      "step": 16500
+    },
+    {
+      "epoch": 3.994854927048599,
+      "grad_norm": 0.2392578125,
+      "learning_rate": 6.79040289723857e-08,
+      "loss": 2.0972,
+      "mean_token_accuracy": 0.5545667923986912,
+      "num_input_tokens_seen": 7994787313,
+      "num_tokens": 3369677528.0,
+      "step": 16550
     }
   ],
   "logging_steps": 50,
   "max_steps": 16568,
-  "num_input_tokens_seen": 7729128049,
+  "num_input_tokens_seen": 8003589233,
   "num_train_epochs": 4,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -3510,12 +3629,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.0676171893972582e+18,
+  "total_flos": 2.141038234858414e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null