Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2318d0fef950a986694f54deb8ab4cf01117572bb0efac7f186953d23af5ad0
+oid sha256:83d948451e5922cc308cd8a10cf8844777bbe3eeeccc2dc67b9a6ce79b72d2e0
 size 557912620

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46ce8e7104cb0d199007b89f3373af5f910884014346c1f945611f4159dafb37
+oid sha256:bfaabb05a95a662d8c7f2b443387597a915505fea3f5272e20297b4175887ada
 size 1115579834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bffa0c819d4bb9f16a80c0c37a452508456cc1e3725c086d1afb6ca62a842d06
+oid sha256:240e6a8ec9456bd6463406cd6d4517d0833e6ea5d37262a07e1e58851593128e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55747937ecf5eb52214b61898d359fcd6713947b12fe4e4bb1c3f1d9bb05147
+oid sha256:46c8da14363ee970453deb0abfc423b52e8f626b95704d94bd6a144124c361a4
 size 1064

last-checkpoint/trainer_state.json

@@ -2,89 +2,40 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 0.3526093088857546,
   "eval_steps": 500,
-  "global_step": 2836,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.08815232722143865,
-      "grad_norm": 70428.5859375,
+      "grad_norm": 48028.53125,
       "learning_rate": 4.561001410437236e-05,
-      "loss": 0.7226,
+      "loss": 0.7241,
       "step": 250
     },
     {
       "epoch": 0.1763046544428773,
-      "grad_norm": 3365.8193359375,
+      "grad_norm": 36453.3671875,
       "learning_rate": 4.120239774330042e-05,
-      "loss": 0.0024,
+      "loss": 0.0023,
       "step": 500
     },
     {
       "epoch": 0.2644569816643159,
-      "grad_norm": 13511.3369140625,
+      "grad_norm": 20.423324584960938,
       "learning_rate": 3.679478138222849e-05,
-      "loss": 0.0017,
+      "loss": 0.002,
       "step": 750
     },
     {
       "epoch": 0.3526093088857546,
-      "grad_norm": 4.582444190979004,
+      "grad_norm": 13388.93359375,
       "learning_rate": 3.2387165021156564e-05,
-      "loss": 0.001,
+      "loss": 0.0013,
       "step": 1000
-    },
-    {
-      "epoch": 0.4407616361071932,
-      "grad_norm": 0.13739077746868134,
-      "learning_rate": 2.7979548660084627e-05,
-      "loss": 0.0014,
-      "step": 1250
-    },
-    {
-      "epoch": 0.5289139633286318,
-      "grad_norm": 0.4030902683734894,
-      "learning_rate": 2.3571932299012694e-05,
-      "loss": 0.0009,
-      "step": 1500
-    },
-    {
-      "epoch": 0.6170662905500706,
-      "grad_norm": 0.12574627995491028,
-      "learning_rate": 1.9164315937940765e-05,
-      "loss": 0.0007,
-      "step": 1750
-    },
-    {
-      "epoch": 0.7052186177715092,
-      "grad_norm": 44621.296875,
-      "learning_rate": 1.4756699576868829e-05,
-      "loss": 0.0008,
-      "step": 2000
-    },
-    {
-      "epoch": 0.7933709449929478,
-      "grad_norm": 0.33594566583633423,
-      "learning_rate": 1.0349083215796897e-05,
-      "loss": 0.0007,
-      "step": 2250
-    },
-    {
-      "epoch": 0.8815232722143864,
-      "grad_norm": 0.1653057485818863,
-      "learning_rate": 5.9414668547249645e-06,
-      "loss": 0.0005,
-      "step": 2500
-    },
-    {
-      "epoch": 0.9696755994358252,
-      "grad_norm": 0.1457623541355133,
-      "learning_rate": 1.5338504936530325e-06,
-      "loss": 0.0003,
-      "step": 2750
     }
   ],
   "logging_steps": 250,
@@ -99,12 +50,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 6914716304670720.0,
+  "total_flos": 2438945832960000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c50f85abe2f9f87d77a104ab25ad9e082538346fe9a00e412724e38efb8769
+oid sha256:82e1fff4aa6ebb74f131111c81ce09fa980fc1c278f9966b7f656b1771ea0a7e
 size 5432