Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dacb143c7ab743e9aaddb52ceaf8b2d3084857f91906714dacd8f4f10e36a82
+oid sha256:bb43ce76c4f73c62e5a6e85da42fdc904f58fe828e868bbdf0be267f32e07824
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2c3217f16b577cba185ae98ad2a5674a8db2b9276059cf21350bdea694fad62
+oid sha256:1312dd678cab7506a32c4aa5817acdf405183ef96aaa93d2a4596d6393378d5e
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:471c196d464571a2d3eaa8b56640d706baf43a5fa29db23527981ea674d1cc5d
+size 14469

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c4d5d330fd2d21389f18d92d837b7b74326019eda8d0aeef699b67f0b194b16
+size 14469

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f41ef2dc3a9c7dccaf66ef3850e86a97c631081c0fdfdaff5d6a0ce628b0f4f
+size 14469

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e510800460c42b7b67d24fb27b7099f5c726a948ffebcd7c17501379991ee2ac
+size 14469

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efbb381c554d799e91db094a8bca7f05b6f679e8066823bcdfc6ea2811eb3c3f
+size 14469

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd2f2645726a3a2f552a52307dc452892e105e7f362ac69985b42f39311f70b
+size 14469

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b974ebc6afa793677214cfcffe57d9f4d7c8e0bd2a082dbc6a3d57bc57e69ab3
+size 14469

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df311cc38c26f5641e0477ca47e8af66bb548ffec021086203c4970526e3a77
+size 14469

last-checkpoint/trainer_state.json

@@ -6,87 +6,87 @@
   "eval_steps": 100,
   "global_step": 500,
   "is_hyper_param_search": false,
-  "is_local_process_zero": true,
+  "is_local_process_zero": false,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.1,
-      "grad_norm": 1.297243595123291,
+      "grad_norm": 11.13700008392334,
       "learning_rate": 0.0003973800426880847,
-      "loss": 9.179060668945313,
+      "loss": 66.094375,
       "step": 100
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 0.09053816046966733,
-      "eval_loss": 8.474776268005371,
-      "eval_runtime": 32.6103,
-      "eval_samples_per_second": 30.665,
-      "eval_steps_per_second": 30.665,
+      "eval_accuracy": 0.10251663405088063,
+      "eval_loss": 62.88532638549805,
+      "eval_runtime": 12.9078,
+      "eval_samples_per_second": 9.684,
+      "eval_steps_per_second": 1.24,
       "step": 100
     },
     {
       "epoch": 0.2,
-      "grad_norm": 1.142166256904602,
+      "grad_norm": 6.741835117340088,
       "learning_rate": 0.0003762085737488283,
-      "loss": 8.30135498046875,
+      "loss": 62.0001123046875,
       "step": 200
     },
     {
       "epoch": 0.2,
-      "eval_accuracy": 0.10549706457925637,
-      "eval_loss": 8.138654708862305,
-      "eval_runtime": 26.7248,
-      "eval_samples_per_second": 37.418,
-      "eval_steps_per_second": 37.418,
+      "eval_accuracy": 0.11803913894324854,
+      "eval_loss": 61.526912689208984,
+      "eval_runtime": 8.6535,
+      "eval_samples_per_second": 14.445,
+      "eval_steps_per_second": 1.849,
       "step": 200
     },
     {
       "epoch": 0.3,
-      "grad_norm": 1.286571741104126,
+      "grad_norm": 7.0108513832092285,
       "learning_rate": 0.00033594217168615465,
-      "loss": 7.987710571289062,
+      "loss": 61.543701171875,
       "step": 300
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.11159295499021527,
-      "eval_loss": 7.991443157196045,
-      "eval_runtime": 26.5785,
-      "eval_samples_per_second": 37.624,
-      "eval_steps_per_second": 37.624,
+      "eval_accuracy": 0.11293346379647749,
+      "eval_loss": 60.98686599731445,
+      "eval_runtime": 8.6635,
+      "eval_samples_per_second": 14.428,
+      "eval_steps_per_second": 1.847,
       "step": 300
     },
     {
       "epoch": 0.4,
-      "grad_norm": 1.262372612953186,
+      "grad_norm": 10.79574203491211,
       "learning_rate": 0.00028094432596115747,
-      "loss": 7.810901489257812,
+      "loss": 61.318671875,
       "step": 400
     },
     {
       "epoch": 0.4,
-      "eval_accuracy": 0.10483365949119373,
-      "eval_loss": 7.9381818771362305,
-      "eval_runtime": 26.6986,
-      "eval_samples_per_second": 37.455,
-      "eval_steps_per_second": 37.455,
+      "eval_accuracy": 0.1016477495107632,
+      "eval_loss": 61.48467254638672,
+      "eval_runtime": 8.6224,
+      "eval_samples_per_second": 14.497,
+      "eval_steps_per_second": 1.856,
       "step": 400
     },
     {
       "epoch": 0.5,
-      "grad_norm": 1.2876827716827393,
+      "grad_norm": 6.4634199142456055,
       "learning_rate": 0.00021717490653764342,
-      "loss": 7.900021362304687,
+      "loss": 60.952919921875,
       "step": 500
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.11435420743639922,
-      "eval_loss": 7.851724624633789,
-      "eval_runtime": 26.5522,
-      "eval_samples_per_second": 37.662,
-      "eval_steps_per_second": 37.662,
+      "eval_accuracy": 0.09600978473581213,
+      "eval_loss": 61.699729919433594,
+      "eval_runtime": 8.3835,
+      "eval_samples_per_second": 14.91,
+      "eval_steps_per_second": 1.909,
       "step": 500
     }
   ],

last-checkpoint/training_args.bin

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