Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee3dcc6ee910f9b7091986fac9897234201849f91a6a2d070f0151d31a3f24a4
+oid sha256:66178a76e2e538ab6e342d35d4825b54fb08bc7578c7f109ed6078644b924e57
 size 14483498224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5590ce31ca67611569f3ee9618b3e4cc8e211008c77245896ee5b02009a5d425
+oid sha256:746f096c66d8710446f9de2a6693a158809fc4412c46e38fd8a89be0d932f54f
 size 28967187355

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e10df580efad97bb633668d65429a37f5f53374d3373d28957a85a8b301eb78e
+oid sha256:d816652875af5b096437609afdf7a105e45a5aed127110ed63352bdde6ad2657
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.390625,
+  "epoch": 0.78125,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -108,6 +108,106 @@
       "mean_token_accuracy": 0.9919667416810989,
       "num_tokens": 3070032.0,
       "step": 500
+    },
+    {
+      "entropy": 0.032282271897420285,
+      "epoch": 0.4296875,
+      "grad_norm": 0.099609375,
+      "learning_rate": 1.7456597222222224e-05,
+      "loss": 0.024263689517974852,
+      "mean_token_accuracy": 0.9916365548968316,
+      "num_tokens": 3371923.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.02768919712398201,
+      "epoch": 0.46875,
+      "grad_norm": 0.154296875,
+      "learning_rate": 1.7022569444444446e-05,
+      "loss": 0.02068368673324585,
+      "mean_token_accuracy": 0.9922330856323243,
+      "num_tokens": 3681052.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.027916706460528077,
+      "epoch": 0.5078125,
+      "grad_norm": 0.146484375,
+      "learning_rate": 1.6588541666666667e-05,
+      "loss": 0.02017390251159668,
+      "mean_token_accuracy": 0.9925840869545937,
+      "num_tokens": 3985154.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.024339500861242414,
+      "epoch": 0.546875,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 1.615451388888889e-05,
+      "loss": 0.017752493619918822,
+      "mean_token_accuracy": 0.992968330681324,
+      "num_tokens": 4294960.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.02500485216733068,
+      "epoch": 0.5859375,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 1.5720486111111114e-05,
+      "loss": 0.018282731771469118,
+      "mean_token_accuracy": 0.9928615567088127,
+      "num_tokens": 4596846.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.023879703185521066,
+      "epoch": 0.625,
+      "grad_norm": 0.158203125,
+      "learning_rate": 1.5286458333333335e-05,
+      "loss": 0.017627782821655273,
+      "mean_token_accuracy": 0.9931773543357849,
+      "num_tokens": 4904237.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.02569641772657633,
+      "epoch": 0.6640625,
+      "grad_norm": 0.09765625,
+      "learning_rate": 1.4852430555555556e-05,
+      "loss": 0.01919528007507324,
+      "mean_token_accuracy": 0.9929538157582283,
+      "num_tokens": 5205258.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.02546143492218107,
+      "epoch": 0.703125,
+      "grad_norm": 0.1162109375,
+      "learning_rate": 1.4418402777777778e-05,
+      "loss": 0.018223344087600707,
+      "mean_token_accuracy": 0.9930938303470611,
+      "num_tokens": 5511048.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.023580400524660945,
+      "epoch": 0.7421875,
+      "grad_norm": 0.1611328125,
+      "learning_rate": 1.3984375000000001e-05,
+      "loss": 0.01719343423843384,
+      "mean_token_accuracy": 0.9934566602110863,
+      "num_tokens": 5824149.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.022929171579889954,
+      "epoch": 0.78125,
+      "grad_norm": 0.19921875,
+      "learning_rate": 1.3550347222222224e-05,
+      "loss": 0.016624774932861328,
+      "mean_token_accuracy": 0.9935434520244598,
+      "num_tokens": 6133395.0,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -127,7 +227,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4446972723750502e+17,
+  "total_flos": 2.885719471186084e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null