Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe589389cc62a42ea44b788b1b490fc62abb8a57c25bb38cb7066eee84ac6cc
+oid sha256:3e02243c2eb7ce0ac0f7e6a4fc0aebd0c8e94867eb18c03a4df7cd03e52f5270
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d48f2fce2ddb0f1ab81abce7e3b67d37300c88dd61c2ebc6a5b680d3e12ea63b
+oid sha256:de9ef13a0217aee1642910133ef911b7ee7db4b71d9d050384aa1527c2f0718d
 size 61392180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff09dd851b3e3105a5a49a8c1669dac36cbebc8c4023852aec01ed6cf3445f9
+oid sha256:8ad7af62d4c1000764e9ecfd0336d5437508d742f8c53b72b4e2523928fa4ab1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0044488933377822264,
+  "epoch": 0.008897786675564453,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 2.736,
       "eval_steps_per_second": 2.736,
       "step": 25
+    },
+    {
+      "epoch": 0.005338672005338672,
+      "grad_norm": 0.21470601856708527,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.857,
+      "step": 30
+    },
+    {
+      "epoch": 0.006228450672895117,
+      "grad_norm": 0.20082759857177734,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8309,
+      "step": 35
+    },
+    {
+      "epoch": 0.007118229340451563,
+      "grad_norm": 0.1999746710062027,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8233,
+      "step": 40
+    },
+    {
+      "epoch": 0.008008008008008008,
+      "grad_norm": 0.213407963514328,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8172,
+      "step": 45
+    },
+    {
+      "epoch": 0.008897786675564453,
+      "grad_norm": 0.19997364282608032,
+      "learning_rate": 0.0,
+      "loss": 0.8318,
+      "step": 50
+    },
+    {
+      "epoch": 0.008897786675564453,
+      "eval_loss": 0.8381756544113159,
+      "eval_runtime": 7304.3471,
+      "eval_samples_per_second": 2.735,
+      "eval_steps_per_second": 2.735,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -72,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.75713949171712e+16,
+  "total_flos": 5.51427898343424e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null