Training in progress, step 2000

{checkpoint-1000 → checkpoint-2000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9916392e176b611154ca5aa0a1a5e7316cc75345b1565faac0a012fbefd61880
+oid sha256:c58f2992dce0a276542ee3f8a596878b450adfca2d0f5d0e4de79226ca26aeb4
 size 267028677

{checkpoint-1000 → checkpoint-2000}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b65f4c874c6086abf0a4c39f04d0375a87a126c9f6b6b673374a1871ded2bb2
+oid sha256:8826b5e400ad3e74a54646acac0427e30e9c65f59b522624a3b1972f74b63272
 size 133523761

{checkpoint-1000 → checkpoint-2000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3a6b46be67c0f58cd6d9f1ad08eeec7d1a958b8051fb1c4e4962dfb1c44de08
+oid sha256:54afc05d1dccae527b37df270cb8239795e29851782c9bf4a45384c9f6328912
 size 14575

{checkpoint-1000 → checkpoint-2000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb71878263f0ce7a479763782c1861c87fa63f77a288c7b0b718c5e890b4e7bb
+oid sha256:48528e3911b6482b407d43a6edd7a9bb566d94b939b0306e61e4d57fa64d1556
 size 627

{checkpoint-1000 → checkpoint-2000}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4,
-  "global_step": 1000,
+  "epoch": 0.8,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -38,11 +38,63 @@
       "eval_system_ram_total": 83.48074722290039,
       "eval_system_ram_used": 4.108898162841797,
       "step": 625
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.80016e-05,
+      "loss": 1.0615,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.7049,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 26.091278076171875,
+      "eval_f1": 0.7010538468880997,
+      "eval_gpu_ram_allocated": 0.39355039596557617,
+      "eval_gpu_ram_cached": 16.05078125,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 33,
+      "eval_loss": 1.002210259437561,
+      "eval_precision": 0.7064795769852438,
+      "eval_recall": 0.7049,
+      "eval_runtime": 15.2502,
+      "eval_samples_per_second": 1311.462,
+      "eval_steps_per_second": 40.983,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 3.858478546142578,
+      "step": 1250
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.70016e-05,
+      "loss": 0.9804,
+      "step": 1875
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.71915,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 26.464637756347656,
+      "eval_f1": 0.7157918638422971,
+      "eval_gpu_ram_allocated": 0.39350461959838867,
+      "eval_gpu_ram_cached": 16.05078125,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 33,
+      "eval_loss": 0.9258390665054321,
+      "eval_precision": 0.7200804939824763,
+      "eval_recall": 0.71915,
+      "eval_runtime": 15.2672,
+      "eval_samples_per_second": 1310.0,
+      "eval_steps_per_second": 40.937,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 3.863994598388672,
+      "step": 1875
     }
   ],
   "max_steps": 12500,
   "num_train_epochs": 5,
-  "total_flos": 503558180662656.0,
+  "total_flos": 1019551625041152.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff78205a97987dc9074782fcd48cb56dbb3f315c6edc25c0ecc1589c5f457a4
+oid sha256:8826b5e400ad3e74a54646acac0427e30e9c65f59b522624a3b1972f74b63272
 size 133523761

runs/Jul23_01-08-06_df8adf32a670/events.out.tfevents.1690074496.df8adf32a670.1420.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2128eddd3b9d716b399d99285a548eceb262fe76ee8cb34fbe1db81700e4cd7f
-size 7086
+oid sha256:c50b8bb682d6275760271c592320a8d9cb71e5ffd04be6620fc4303d5dc835f1
+size 8188