Training in progress, step 10, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf8acb1736feb9f9c5744dff791935d4ee71340ef84e99e799cecec44ef1fba4
+oid sha256:43e8cce973730ae1df8b4f8a574251e0eb8d84e53f64786e1e366ca5fe36b401
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e05d6bc58e1920866c2f6e583cd7a9d3c80b7f5e6a77d49cc0d9c8a26a08af8
+oid sha256:a037b3fb1050b981c2566e360b0f7bc7e519dcafb84360257615f51166e12d0f
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47750b38402e142f696be83e692f0dcaeaec3650f3a539a8172bb90643534bb3
+oid sha256:df9402a6cb264811460962fe076b4b0afaf8b5c58042e7c96e291b0ab753e219
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a571280ee41c7271d53b8310f62e388e2b05dcdc4ed27f67ba6b3018cacc34ae
+oid sha256:b7a69ede4fdf179c7e9afdb737d70a6ea7d15e0d098b2d3fc81819822f211425
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ce995976843ea29dcf27303959f0b6a782b62ac5ec5d7682e78bdf61d82c85
+oid sha256:d67d86f802b2679f6c40dd9bf098b476c8f516c4ab864429fede96230ce6fe23
 size 1465

last-checkpoint/trainer_state.json

@@ -2,206 +2,37 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1,
+  "epoch": 0.01,
   "eval_steps": 5,
-  "global_step": 100,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.005,
-      "eval_accuracy": 3.92156862745098e-06,
-      "eval_loss": 21.843835830688477,
-      "eval_runtime": 45.1096,
-      "eval_samples_per_second": 11.084,
-      "eval_steps_per_second": 5.542,
+      "eval_accuracy": 0.05346666666666667,
+      "eval_loss": 20.794218063354492,
+      "eval_runtime": 35.3413,
+      "eval_samples_per_second": 14.148,
+      "eval_steps_per_second": 7.074,
       "step": 5
     },
     {
       "epoch": 0.01,
-      "eval_accuracy": 0.005796078431372549,
-      "eval_loss": 21.70684814453125,
-      "eval_runtime": 44.6216,
-      "eval_samples_per_second": 11.205,
-      "eval_steps_per_second": 5.603,
+      "eval_accuracy": 0.07933333333333334,
+      "eval_loss": 19.725038528442383,
+      "eval_runtime": 35.9943,
+      "eval_samples_per_second": 13.891,
+      "eval_steps_per_second": 6.946,
       "step": 10
-    },
-    {
-      "epoch": 0.015,
-      "eval_accuracy": 0.019337254901960785,
-      "eval_loss": 21.580129623413086,
-      "eval_runtime": 45.0557,
-      "eval_samples_per_second": 11.097,
-      "eval_steps_per_second": 5.549,
-      "step": 15
-    },
-    {
-      "epoch": 0.02,
-      "eval_accuracy": 0.022207843137254903,
-      "eval_loss": 21.46198081970215,
-      "eval_runtime": 45.1875,
-      "eval_samples_per_second": 11.065,
-      "eval_steps_per_second": 5.533,
-      "step": 20
-    },
-    {
-      "epoch": 0.025,
-      "eval_accuracy": 0.029156862745098037,
-      "eval_loss": 21.34127426147461,
-      "eval_runtime": 45.3567,
-      "eval_samples_per_second": 11.024,
-      "eval_steps_per_second": 5.512,
-      "step": 25
-    },
-    {
-      "epoch": 0.03,
-      "eval_accuracy": 0.03545098039215686,
-      "eval_loss": 21.242088317871094,
-      "eval_runtime": 45.3984,
-      "eval_samples_per_second": 11.014,
-      "eval_steps_per_second": 5.507,
-      "step": 30
-    },
-    {
-      "epoch": 0.035,
-      "eval_accuracy": 0.042094117647058824,
-      "eval_loss": 21.127534866333008,
-      "eval_runtime": 46.4511,
-      "eval_samples_per_second": 10.764,
-      "eval_steps_per_second": 5.382,
-      "step": 35
-    },
-    {
-      "epoch": 0.04,
-      "eval_accuracy": 0.05104313725490196,
-      "eval_loss": 21.007797241210938,
-      "eval_runtime": 45.2887,
-      "eval_samples_per_second": 11.04,
-      "eval_steps_per_second": 5.52,
-      "step": 40
-    },
-    {
-      "epoch": 0.045,
-      "eval_accuracy": 0.05892549019607843,
-      "eval_loss": 20.8879451751709,
-      "eval_runtime": 45.4919,
-      "eval_samples_per_second": 10.991,
-      "eval_steps_per_second": 5.495,
-      "step": 45
-    },
-    {
-      "epoch": 0.05,
-      "eval_accuracy": 0.06429411764705882,
-      "eval_loss": 20.779932022094727,
-      "eval_runtime": 45.3237,
-      "eval_samples_per_second": 11.032,
-      "eval_steps_per_second": 5.516,
-      "step": 50
-    },
-    {
-      "epoch": 0.055,
-      "eval_accuracy": 0.06933333333333333,
-      "eval_loss": 20.666351318359375,
-      "eval_runtime": 45.5272,
-      "eval_samples_per_second": 10.982,
-      "eval_steps_per_second": 5.491,
-      "step": 55
-    },
-    {
-      "epoch": 0.06,
-      "eval_accuracy": 0.0722156862745098,
-      "eval_loss": 20.56865692138672,
-      "eval_runtime": 45.4567,
-      "eval_samples_per_second": 10.999,
-      "eval_steps_per_second": 5.5,
-      "step": 60
-    },
-    {
-      "epoch": 0.065,
-      "eval_accuracy": 0.07492549019607843,
-      "eval_loss": 20.474367141723633,
-      "eval_runtime": 45.2841,
-      "eval_samples_per_second": 11.041,
-      "eval_steps_per_second": 5.521,
-      "step": 65
-    },
-    {
-      "epoch": 0.07,
-      "eval_accuracy": 0.07572941176470588,
-      "eval_loss": 20.385995864868164,
-      "eval_runtime": 45.3374,
-      "eval_samples_per_second": 11.028,
-      "eval_steps_per_second": 5.514,
-      "step": 70
-    },
-    {
-      "epoch": 0.075,
-      "eval_accuracy": 0.07717254901960785,
-      "eval_loss": 20.2958984375,
-      "eval_runtime": 45.3438,
-      "eval_samples_per_second": 11.027,
-      "eval_steps_per_second": 5.513,
-      "step": 75
-    },
-    {
-      "epoch": 0.08,
-      "eval_accuracy": 0.07829411764705882,
-      "eval_loss": 20.204992294311523,
-      "eval_runtime": 45.427,
-      "eval_samples_per_second": 11.007,
-      "eval_steps_per_second": 5.503,
-      "step": 80
-    },
-    {
-      "epoch": 0.085,
-      "eval_accuracy": 0.07968235294117647,
-      "eval_loss": 20.112102508544922,
-      "eval_runtime": 45.0567,
-      "eval_samples_per_second": 11.097,
-      "eval_steps_per_second": 5.549,
-      "step": 85
-    },
-    {
-      "epoch": 0.09,
-      "eval_accuracy": 0.07994509803921569,
-      "eval_loss": 20.023468017578125,
-      "eval_runtime": 45.1806,
-      "eval_samples_per_second": 11.067,
-      "eval_steps_per_second": 5.533,
-      "step": 90
-    },
-    {
-      "epoch": 0.095,
-      "eval_accuracy": 0.07969411764705882,
-      "eval_loss": 19.922317504882812,
-      "eval_runtime": 45.3425,
-      "eval_samples_per_second": 11.027,
-      "eval_steps_per_second": 5.514,
-      "step": 95
-    },
-    {
-      "epoch": 0.1,
-      "grad_norm": 3.734435558319092,
-      "learning_rate": 3.973800426880847e-06,
-      "loss": 167.01556640625,
-      "step": 100
-    },
-    {
-      "epoch": 0.1,
-      "eval_accuracy": 0.07997254901960785,
-      "eval_loss": 19.829484939575195,
-      "eval_runtime": 45.4368,
-      "eval_samples_per_second": 11.004,
-      "eval_steps_per_second": 5.502,
-      "step": 100
     }
   ],
   "logging_steps": 100,
   "max_steps": 1000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
-  "save_steps": 100,
+  "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61901a80b548b22f93a9c3be114cffc81cb96a048a415d030c20431d54e95e01
+oid sha256:9bdaf07830b33937d6f32edfcc276b67b7d1e1e7aade843e68aded14ec567bf9
 size 5265