Training in progress, step 9, checkpoint

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b347053b06b3c619535ebc10f28a094fccd287e10c86393ad57e0922ee6235
+oid sha256:f037179e2f72f8052c567935428a2b336875a279f6a258c94c81c6eda52ca9a7
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6625b271af64d78b0cb21cd2181dec43ed26cbdaf7c144448da19978546a31f
+oid sha256:095e7bf64776870b00aad21b5d20fedc85a0ea0239296af560cd4be957fbf562
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33fa0c08b85797649036972335a8cd73b92d730982f9c6331cf9c606a49c949f
+oid sha256:4c7ea82e6f493a6775b5a4cd8618f2ddb43db4405ab77c46f046a09ea763e869
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33597b58fea822d53100c04ad5bf6dac139f8ee7ebeccc1eeff0d0f0c5705911
+oid sha256:d74456313175ad9b8126678aa9443bfe6356fb4c5d663a059450d3f27587e784
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6e8dc2cb5ce182cb23e477a3c983eadfda3e659ec882f4a3cc3deb0891b781e
+oid sha256:14afc2d953ce2b165f4da7b4bca19afec155ff1d5805a54379b64f4c34bfd6a9
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b680b229241711413bb5dfcac9eefb7d9456a473f950e8a7e515db460a59ca55
+oid sha256:ed57cfed487b9d17510809e80ef03db1018bf9797a8332cd83d8598a8bf8276d
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bae373d23ff7545032b25d9d95aaecf06cb3497437725166582db64db01deef4
+oid sha256:f9ca5a0af0b68b10972e265eafc5246b223cb21b68105b011c346e7cb46fee64
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:734648406d7d04253f7d286c1e4582bd2c99e8fd94850aee383e98ceb2e73b85
+oid sha256:c8061970669cd0d8e3da8a8bb44cab4dd909f46d3ec4e8db91363c4c8a1e4dc2
 size 15984

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00967741935483871,
+  "epoch": 0.014516129032258065,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 43.73,
       "eval_steps_per_second": 5.487,
       "step": 6
+    },
+    {
+      "epoch": 0.01129032258064516,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 9.2474,
+      "step": 7
+    },
+    {
+      "epoch": 0.012903225806451613,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 9.5729,
+      "step": 8
+    },
+    {
+      "epoch": 0.014516129032258065,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 9.5663,
+      "step": 9
+    },
+    {
+      "epoch": 0.014516129032258065,
+      "eval_loss": 9.502001762390137,
+      "eval_runtime": 23.8764,
+      "eval_samples_per_second": 43.725,
+      "eval_steps_per_second": 5.487,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.770634359078912e+16,
+  "total_flos": 2.655951538618368e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null