Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62b0ae2bece445149d95dac8be318a1e3cf663dc984da1c6c1763a330dde2ae
+oid sha256:ba163da7ac5c05dca7b23ba9ae84e43000a41894b62d4b0bd6c156263a09d667
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db3b73b9e39e57f14acc8da4a5a2ee7f1b952789fcd7ddf666c5f54ad92c0646
+oid sha256:228620246956b9c20bcf1b4373421a28779315491724ca8b3e1ccf5acdfefaac
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21dfc6c263d5ad0f8ba77e03600244b9f2781e61ae66cba4cff3c2ce6c58574f
+oid sha256:6d2d83df56a301a7a031ee1a2baca538bacda8ebe202ee2460e255209acd4857
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6359143556c6c392e65dff6e223cd73982950d740ede67b2be0a429a6648f6d5
+oid sha256:f5bdf0f87d77b7de3138456a39226e05b8a47b0bad9a0f4dd8d726aafd08598b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.999080987937967,
+  "epoch": 8.998966111430212,
   "eval_steps": 50,
-  "global_step": 2176,
+  "global_step": 2448,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -652,6 +652,81 @@
       "eval_samples_per_second": 41.646,
       "eval_steps_per_second": 20.823,
       "step": 2150
+    },
+    {
+      "epoch": 8.087306145893164,
+      "grad_norm": 45.93680191040039,
+      "learning_rate": 1.9117647058823528e-05,
+      "loss": 0.8363,
+      "step": 2200
+    },
+    {
+      "epoch": 8.087306145893164,
+      "eval_loss": 1.2366794347763062,
+      "eval_runtime": 115.7882,
+      "eval_samples_per_second": 41.68,
+      "eval_steps_per_second": 20.84,
+      "step": 2200
+    },
+    {
+      "epoch": 8.271108558299828,
+      "grad_norm": 73.48126983642578,
+      "learning_rate": 1.7279411764705884e-05,
+      "loss": 0.8333,
+      "step": 2250
+    },
+    {
+      "epoch": 8.271108558299828,
+      "eval_loss": 1.2330245971679688,
+      "eval_runtime": 115.848,
+      "eval_samples_per_second": 41.658,
+      "eval_steps_per_second": 20.829,
+      "step": 2250
+    },
+    {
+      "epoch": 8.454910970706491,
+      "grad_norm": 76.98050689697266,
+      "learning_rate": 1.5441176470588237e-05,
+      "loss": 0.8267,
+      "step": 2300
+    },
+    {
+      "epoch": 8.454910970706491,
+      "eval_loss": 1.2376160621643066,
+      "eval_runtime": 115.9174,
+      "eval_samples_per_second": 41.633,
+      "eval_steps_per_second": 20.817,
+      "step": 2300
+    },
+    {
+      "epoch": 8.638713383113153,
+      "grad_norm": 128.97714233398438,
+      "learning_rate": 1.3602941176470587e-05,
+      "loss": 0.8217,
+      "step": 2350
+    },
+    {
+      "epoch": 8.638713383113153,
+      "eval_loss": 1.2340155839920044,
+      "eval_runtime": 115.9099,
+      "eval_samples_per_second": 41.636,
+      "eval_steps_per_second": 20.818,
+      "step": 2350
+    },
+    {
+      "epoch": 8.822515795519816,
+      "grad_norm": 55.4945182800293,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 0.8221,
+      "step": 2400
+    },
+    {
+      "epoch": 8.822515795519816,
+      "eval_loss": 1.2404063940048218,
+      "eval_runtime": 116.0058,
+      "eval_samples_per_second": 41.601,
+      "eval_steps_per_second": 20.801,
+      "step": 2400
     }
   ],
   "logging_steps": 50,
@@ -671,7 +746,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.614783797825372e+17,
+  "total_flos": 6.316931268340613e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null