Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e9e00e00c215ffdf92be72fd53a14e0bd66fcc66f178b041e605d8f49e85aa4
+oid sha256:fa30a353c5702160269107953e449180da3586d949c41cf465b64cd044dc232c
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e847a7f0f2b7bcc1bb383a8be2e34d5a450ae70e26f7342f62739328b928e80
+oid sha256:4e2319b69e516a84a6e457adbe461a753cf4f5faf6524acafe5a536c821999fd
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0facf3338e35fed3aa8b3aca0cf2da64c5da32895aac2f3f8e801c8e7b375af7
+oid sha256:5cbd751356e453a1409e86df4b77aad42724a61a6be4c4b308dbafc04292ef5d
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c7b0b351bc503daa25d30efed64ec63ddc9211784a016b82910d2b20dc1594
+oid sha256:3ad75cba455056d8144bc4035ffaf4449f622d73337d0496743a9320673580ff
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a50aafb0b75e3d7565f4919496800f406afe868bb8e9e4f5b436535c2d73dfb
+oid sha256:4d7a592f82eb7c329fc583c5aac235a4c92380a21cffb63b75704b43c0d7da21
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25461652a2e14e143efd7d90db238b616244de8f3d007bf5de08ae47ca77c458
+oid sha256:864f7132014bd3eb1703ae571369f9ee5574b56dba80deb2835c22872503c57c
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4608,
+  "epoch": 0.5184,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 228.018,
       "eval_steps_per_second": 7.153,
       "step": 72
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6900295615196228,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.0248,
+      "step": 75
+    },
+    {
+      "epoch": 0.4992,
+      "grad_norm": 0.9134931564331055,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.0247,
+      "step": 78
+    },
+    {
+      "epoch": 0.5184,
+      "grad_norm": 0.7832142114639282,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.0234,
+      "step": 81
+    },
+    {
+      "epoch": 0.5184,
+      "eval_loss": 1.9945977926254272,
+      "eval_runtime": 4.596,
+      "eval_samples_per_second": 228.897,
+      "eval_steps_per_second": 7.18,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1621247991834214e+17,
+  "total_flos": 1.3068877510056346e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null