Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47630d4c3006b50921d7e36c744d50be38e8879aea194e330ca9b15f1daaafd3
+oid sha256:192259f2c1b4d88d789b5c489ca9003298f60ecbe0b848a8d37411dcd693b958
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:697d38dc27773b03d627eaea47fe209ad4c1e9a4073dc7b3d8e4eec46920a338
+oid sha256:a386ca0bda826444b25bbba60d0adc8beec6ba09f5bcc57ab30665a76e50f853
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d27635aa3bf8c9513bde838cce12dd861db1a571c559e6e3d3706dff45fc7a8d
+oid sha256:6bf3f3c24bb80a8453d4f69a54971bc84e22f4d6c02bfcca11e053397356566a
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95b96648dba4a14572860ec64f84946a5310ebc9249f9d3352c1018256aeef8
+oid sha256:ea9b67c97ec0b0a1b79a6330badd5da865b550616c82ba334622fd4f95186829
 size 1064

last-checkpoint/trainer_state.json

@@ -1,132 +1,27 @@
 {
-  "best_metric": 1.1703433990478516,
-  "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-800",
-  "epoch": 0.23222060957910015,
+  "best_metric": 1.2662084102630615,
+  "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-100",
+  "epoch": 0.02902757619738752,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.02902757619738752,
-      "grad_norm": 0.5972162485122681,
-      "learning_rate": 0.0009970972423802612,
-      "loss": 3.1833,
+      "grad_norm": 1.131932258605957,
+      "learning_rate": 9.970972423802612e-05,
+      "loss": 2.8244,
       "step": 100
     },
     {
       "epoch": 0.02902757619738752,
-      "eval_loss": 1.3059791326522827,
-      "eval_runtime": 213.3119,
-      "eval_samples_per_second": 213.298,
-      "eval_steps_per_second": 3.333,
+      "eval_loss": 1.2662084102630615,
+      "eval_runtime": 213.5614,
+      "eval_samples_per_second": 213.049,
+      "eval_steps_per_second": 3.329,
       "step": 100
-    },
-    {
-      "epoch": 0.05805515239477504,
-      "grad_norm": 0.615159809589386,
-      "learning_rate": 0.0009941944847605226,
-      "loss": 2.7965,
-      "step": 200
-    },
-    {
-      "epoch": 0.05805515239477504,
-      "eval_loss": 1.2634466886520386,
-      "eval_runtime": 213.6629,
-      "eval_samples_per_second": 212.948,
-      "eval_steps_per_second": 3.328,
-      "step": 200
-    },
-    {
-      "epoch": 0.08708272859216255,
-      "grad_norm": 0.534396767616272,
-      "learning_rate": 0.0009912917271407838,
-      "loss": 2.6855,
-      "step": 300
-    },
-    {
-      "epoch": 0.08708272859216255,
-      "eval_loss": 1.230128526687622,
-      "eval_runtime": 213.6816,
-      "eval_samples_per_second": 212.929,
-      "eval_steps_per_second": 3.327,
-      "step": 300
-    },
-    {
-      "epoch": 0.11611030478955008,
-      "grad_norm": 0.5327989459037781,
-      "learning_rate": 0.000988388969521045,
-      "loss": 2.618,
-      "step": 400
-    },
-    {
-      "epoch": 0.11611030478955008,
-      "eval_loss": 1.216036319732666,
-      "eval_runtime": 213.4593,
-      "eval_samples_per_second": 213.151,
-      "eval_steps_per_second": 3.331,
-      "step": 400
-    },
-    {
-      "epoch": 0.14513788098693758,
-      "grad_norm": 0.5518757700920105,
-      "learning_rate": 0.0009854862119013062,
-      "loss": 2.5759,
-      "step": 500
-    },
-    {
-      "epoch": 0.14513788098693758,
-      "eval_loss": 1.1977550983428955,
-      "eval_runtime": 213.2072,
-      "eval_samples_per_second": 213.403,
-      "eval_steps_per_second": 3.335,
-      "step": 500
-    },
-    {
-      "epoch": 0.1741654571843251,
-      "grad_norm": 0.5023015141487122,
-      "learning_rate": 0.0009825834542815674,
-      "loss": 2.526,
-      "step": 600
-    },
-    {
-      "epoch": 0.1741654571843251,
-      "eval_loss": 1.1928865909576416,
-      "eval_runtime": 213.533,
-      "eval_samples_per_second": 213.077,
-      "eval_steps_per_second": 3.33,
-      "step": 600
-    },
-    {
-      "epoch": 0.20319303338171263,
-      "grad_norm": 0.5164414048194885,
-      "learning_rate": 0.0009796806966618288,
-      "loss": 2.5121,
-      "step": 700
-    },
-    {
-      "epoch": 0.20319303338171263,
-      "eval_loss": 1.181251049041748,
-      "eval_runtime": 213.4132,
-      "eval_samples_per_second": 213.197,
-      "eval_steps_per_second": 3.332,
-      "step": 700
-    },
-    {
-      "epoch": 0.23222060957910015,
-      "grad_norm": 0.535000205039978,
-      "learning_rate": 0.00097677793904209,
-      "loss": 2.456,
-      "step": 800
-    },
-    {
-      "epoch": 0.23222060957910015,
-      "eval_loss": 1.1703433990478516,
-      "eval_runtime": 213.4281,
-      "eval_samples_per_second": 213.182,
-      "eval_steps_per_second": 3.331,
-      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -155,7 +50,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8003100862316544.0,
+  "total_flos": 1000387607789568.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee0ef74173b2c9a49dca197269030629fd4de03cd43419ed74c4742b9a5dba90
+oid sha256:106cd64593a78067217b619a1bb4288f6aff3cb8411c9fafd726f7129f1b9be1
 size 5368