Training in progress, step 1000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb43ce76c4f73c62e5a6e85da42fdc904f58fe828e868bbdf0be267f32e07824
+oid sha256:cd588dbc728c53e33444470b35f0ec00b32b282a4a741258c3b25ac3abed7937
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1312dd678cab7506a32c4aa5817acdf405183ef96aaa93d2a4596d6393378d5e
+oid sha256:2aad02749c94610ad407ffb13a3c15d2904a2ee0a9ac6a2f501b604d4fadc0ef
 size 1540661735

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fb8116194227284009af0f32eb6c9bf39b120912678b54e07fcb6539f29b5b2
+oid sha256:b815622b7dfb0359193f2c3e6cdc190a4c07e6c28cfbaf526d6da260173bd4a4
 size 14455

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3161ebc22e167d90d7ee5cc1bfde367c6af5f0b04db44c912617eb26a593223
+oid sha256:94b7b1a014f5dad743694fda5858015bfe3bd4c82eac608d649238b91858a560
 size 1465

last-checkpoint/trainer_state.json

@@ -2,92 +2,172 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 1.0,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
-  "is_local_process_zero": false,
+  "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.1,
-      "grad_norm": 11.13700008392334,
+      "grad_norm": 1.297243595123291,
       "learning_rate": 0.0003973800426880847,
-      "loss": 66.094375,
+      "loss": 9.179060668945313,
       "step": 100
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 0.10251663405088063,
-      "eval_loss": 62.88532638549805,
-      "eval_runtime": 12.9078,
-      "eval_samples_per_second": 9.684,
-      "eval_steps_per_second": 1.24,
+      "eval_accuracy": 0.09053816046966733,
+      "eval_loss": 8.474776268005371,
+      "eval_runtime": 32.6103,
+      "eval_samples_per_second": 30.665,
+      "eval_steps_per_second": 30.665,
       "step": 100
     },
     {
       "epoch": 0.2,
-      "grad_norm": 6.741835117340088,
+      "grad_norm": 1.142166256904602,
       "learning_rate": 0.0003762085737488283,
-      "loss": 62.0001123046875,
+      "loss": 8.30135498046875,
       "step": 200
     },
     {
       "epoch": 0.2,
-      "eval_accuracy": 0.11803913894324854,
-      "eval_loss": 61.526912689208984,
-      "eval_runtime": 8.6535,
-      "eval_samples_per_second": 14.445,
-      "eval_steps_per_second": 1.849,
+      "eval_accuracy": 0.10549706457925637,
+      "eval_loss": 8.138654708862305,
+      "eval_runtime": 26.7248,
+      "eval_samples_per_second": 37.418,
+      "eval_steps_per_second": 37.418,
       "step": 200
     },
     {
       "epoch": 0.3,
-      "grad_norm": 7.0108513832092285,
+      "grad_norm": 1.286571741104126,
       "learning_rate": 0.00033594217168615465,
-      "loss": 61.543701171875,
+      "loss": 7.987710571289062,
       "step": 300
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.11293346379647749,
-      "eval_loss": 60.98686599731445,
-      "eval_runtime": 8.6635,
-      "eval_samples_per_second": 14.428,
-      "eval_steps_per_second": 1.847,
+      "eval_accuracy": 0.11159295499021527,
+      "eval_loss": 7.991443157196045,
+      "eval_runtime": 26.5785,
+      "eval_samples_per_second": 37.624,
+      "eval_steps_per_second": 37.624,
       "step": 300
     },
     {
       "epoch": 0.4,
-      "grad_norm": 10.79574203491211,
+      "grad_norm": 1.262372612953186,
       "learning_rate": 0.00028094432596115747,
-      "loss": 61.318671875,
+      "loss": 7.810901489257812,
       "step": 400
     },
     {
       "epoch": 0.4,
-      "eval_accuracy": 0.1016477495107632,
-      "eval_loss": 61.48467254638672,
-      "eval_runtime": 8.6224,
-      "eval_samples_per_second": 14.497,
-      "eval_steps_per_second": 1.856,
+      "eval_accuracy": 0.10483365949119373,
+      "eval_loss": 7.9381818771362305,
+      "eval_runtime": 26.6986,
+      "eval_samples_per_second": 37.455,
+      "eval_steps_per_second": 37.455,
       "step": 400
     },
     {
       "epoch": 0.5,
-      "grad_norm": 6.4634199142456055,
+      "grad_norm": 1.2876827716827393,
       "learning_rate": 0.00021717490653764342,
-      "loss": 60.952919921875,
+      "loss": 7.900021362304687,
       "step": 500
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.09600978473581213,
-      "eval_loss": 61.699729919433594,
-      "eval_runtime": 8.3835,
-      "eval_samples_per_second": 14.91,
-      "eval_steps_per_second": 1.909,
+      "eval_accuracy": 0.11435420743639922,
+      "eval_loss": 7.851724624633789,
+      "eval_runtime": 26.5522,
+      "eval_samples_per_second": 37.662,
+      "eval_steps_per_second": 37.662,
       "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.2628377676010132,
+      "learning_rate": 0.00015154431949464275,
+      "loss": 7.744283447265625,
+      "step": 600
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.1190665362035225,
+      "eval_loss": 7.8012566566467285,
+      "eval_runtime": 27.3957,
+      "eval_samples_per_second": 36.502,
+      "eval_steps_per_second": 36.502,
+      "step": 600
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.3543407917022705,
+      "learning_rate": 9.11646573017482e-05,
+      "loss": 7.696810302734375,
+      "step": 700
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.12185714285714286,
+      "eval_loss": 7.775871276855469,
+      "eval_runtime": 26.9132,
+      "eval_samples_per_second": 37.157,
+      "eval_steps_per_second": 37.157,
+      "step": 700
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.2917762994766235,
+      "learning_rate": 4.2578993244549506e-05,
+      "loss": 7.771747436523437,
+      "step": 800
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.12456751467710372,
+      "eval_loss": 7.751345157623291,
+      "eval_runtime": 26.6293,
+      "eval_samples_per_second": 37.553,
+      "eval_steps_per_second": 37.553,
+      "step": 800
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.3219099044799805,
+      "learning_rate": 1.1052337907897503e-05,
+      "loss": 7.84291015625,
+      "step": 900
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.1239921722113503,
+      "eval_loss": 7.749647617340088,
+      "eval_runtime": 26.5278,
+      "eval_samples_per_second": 37.696,
+      "eval_steps_per_second": 37.696,
+      "step": 900
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.334007978439331,
+      "learning_rate": 1.093583978573065e-09,
+      "loss": 7.778873291015625,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.12396868884540117,
+      "eval_loss": 7.747113227844238,
+      "eval_runtime": 26.6654,
+      "eval_samples_per_second": 37.502,
+      "eval_steps_per_second": 37.502,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -102,7 +182,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eaf4364d37f9f4ceb03f7b16a5643504bb95eb9da30e7cced827582fa3d3389
-size 5265
+oid sha256:b47eb6e798b2dfe4e0fdea550782a8eb56b1b579932ae1b65db9c8ecf145627d
+size 5329