Training in progress, epoch 7, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f7cf4137a88c6295e50c3812c1bd34299d8d8541394fa266ae9f7e6e0dc472
+oid sha256:c5dcee1ea792e118879948269b45b63d453249bb9453c9fa0ca2fc9051ac89a9
 size 2708729576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1441a21a6b8eacb19dada7d96b0390f58ee182d1c1ef9147f521363c955392f5
+oid sha256:e55eb8b2da17b2a5d3ae8a61a6a0044d01b96823a5d885c92f08fa23e0ab6c51
 size 52499200

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252d84a8621f0d8623f524bb8ee54bb1a386d75c0645fcaf9bbfcc4b59877fc1
+oid sha256:5a73f4ec8cc461fdcad0bea4ca4995104cb70648550f70c0efd1720de2eef3ad
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ebd3960ec1614497d0e6e97cebd857464e618edc4df8a50eee43da5ac2ba348
+oid sha256:f1318a37534b462ff16790cf62c003bcdfdf0493594d4a0b3e928e4d2f7999ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.0,
+  "epoch": 7.0,
   "eval_steps": 50,
-  "global_step": 774,
+  "global_step": 903,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,48 @@
       "eval_samples_per_second": 22.004,
       "eval_steps_per_second": 5.501,
       "step": 750
+    },
+    {
+      "epoch": 6.203025866276232,
+      "grad_norm": 300.7341613769531,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.7721,
+      "step": 800
+    },
+    {
+      "epoch": 6.203025866276232,
+      "eval_runtime": 19.6207,
+      "eval_samples_per_second": 22.018,
+      "eval_steps_per_second": 5.504,
+      "step": 800
+    },
+    {
+      "epoch": 6.593460224499756,
+      "grad_norm": 141.74777221679688,
+      "learning_rate": 3.359375e-05,
+      "loss": 1.4889,
+      "step": 850
+    },
+    {
+      "epoch": 6.593460224499756,
+      "eval_runtime": 19.6434,
+      "eval_samples_per_second": 21.992,
+      "eval_steps_per_second": 5.498,
+      "step": 850
+    },
+    {
+      "epoch": 6.98389458272328,
+      "grad_norm": 283.6333923339844,
+      "learning_rate": 2.96875e-05,
+      "loss": 1.5119,
+      "step": 900
+    },
+    {
+      "epoch": 6.98389458272328,
+      "eval_runtime": 19.6441,
+      "eval_samples_per_second": 21.991,
+      "eval_steps_per_second": 5.498,
+      "step": 900
     }
   ],
   "logging_steps": 50,