Training in progress, step 6, checkpoint

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d4deae0bd04f2f5ea5ee94cecba485db67e41f1ad143d622a46c1d2c30dc24
+oid sha256:48b347053b06b3c619535ebc10f28a094fccd287e10c86393ad57e0922ee6235
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea88a8a855052b686c0e9966ad122f8376c64f6f628a7e3104814ab6e0e8690a
+oid sha256:b6625b271af64d78b0cb21cd2181dec43ed26cbdaf7c144448da19978546a31f
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f1af08cdbee3c9c05ac4a6327785c38af6e6b54c69d411300a162e07ca4e61
+oid sha256:33fa0c08b85797649036972335a8cd73b92d730982f9c6331cf9c606a49c949f
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fb12a86162ed6a6f7906ae4cd1a98a9c974e75535c3003515cdbc050d82303
+oid sha256:33597b58fea822d53100c04ad5bf6dac139f8ee7ebeccc1eeff0d0f0c5705911
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e5c0c255bf754c835b684820bf4ffd7fa349271bfcf7e91ebfcba56b3fd24c
+oid sha256:a6e8dc2cb5ce182cb23e477a3c983eadfda3e659ec882f4a3cc3deb0891b781e
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dfc5b2955f9c5d165e0d6b6041198b31364a15e3035b232d3602131e70ff799
+oid sha256:b680b229241711413bb5dfcac9eefb7d9456a473f950e8a7e515db460a59ca55
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d62e9886913e4e96e96b807e4766a0f4d746baf5b1c3ee9573021f4e8ed8218
+oid sha256:bae373d23ff7545032b25d9d95aaecf06cb3497437725166582db64db01deef4
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1536131d8ce0dc61c80b7fac02e22a20264d090173211cc94c7faf830b21909f
+oid sha256:734648406d7d04253f7d286c1e4582bd2c99e8fd94850aee383e98ceb2e73b85
 size 15984

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004838709677419355,
+  "epoch": 0.00967741935483871,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 43.695,
       "eval_steps_per_second": 5.483,
       "step": 3
+    },
+    {
+      "epoch": 0.0064516129032258064,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 9.4681,
+      "step": 4
+    },
+    {
+      "epoch": 0.008064516129032258,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 9.3615,
+      "step": 5
+    },
+    {
+      "epoch": 0.00967741935483871,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 9.3141,
+      "step": 6
+    },
+    {
+      "epoch": 0.00967741935483871,
+      "eval_loss": 9.502001762390137,
+      "eval_runtime": 23.8738,
+      "eval_samples_per_second": 43.73,
+      "eval_steps_per_second": 5.487,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8853171795394560.0,
+  "total_flos": 1.770634359078912e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null