Training in progress, step 77000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a187dee5bccd16e94b5ab10c8dee4691190193326142bcafb73a0a6eb058d93
+oid sha256:4f64707cb242aae96a30c6b449fcc99592355f500c9224203686d1d890be2992
 size 469337272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4576b4611184440e8e89546d8dcec0928f3f749f9bd7cd9939158be70b4eeb74
+oid sha256:10adaaa97072ac420e324e8f48de65dca77077c9e183034ad6853c28043a73f7
 size 938825803

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:375646414b14bb81be31b058ed8af728ea3d95a2e32dca6c4303eaf631e462ed
+oid sha256:754331f5e21dff730a141fc4f1c359fb757055cf0e71500d04c1537884521087
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abf2f313f27bccac25e9c8e915c70451aa8583b1fd70999a373943c42410d5b
+oid sha256:e31d3f2dd7778628805fe0f91bc420be77c7d5b49ef9506f643542e757c4a470
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.36363636363636365,
+  "epoch": 0.012987012987012988,
   "eval_steps": 1000,
-  "global_step": 76000,
+  "global_step": 77000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5936,10 +5936,88 @@
       "eval_samples_per_second": 77.062,
       "eval_steps_per_second": 19.266,
       "step": 76000
+    },
+    {
+      "epoch": 0.0012987012987012987,
+      "grad_norm": 0.16393087804317474,
+      "learning_rate": 3.391192895308981e-07,
+      "loss": 2.6057958984375,
+      "step": 76100
+    },
+    {
+      "epoch": 0.0025974025974025974,
+      "grad_norm": 0.1581353396177292,
+      "learning_rate": 2.6802681023424534e-07,
+      "loss": 2.6045050048828124,
+      "step": 76200
+    },
+    {
+      "epoch": 0.003896103896103896,
+      "grad_norm": 0.16540294885635376,
+      "learning_rate": 2.0528552419035728e-07,
+      "loss": 2.6286279296875,
+      "step": 76300
+    },
+    {
+      "epoch": 0.005194805194805195,
+      "grad_norm": 0.1575717329978943,
+      "learning_rate": 1.508964798905832e-07,
+      "loss": 2.624171142578125,
+      "step": 76400
+    },
+    {
+      "epoch": 0.006493506493506494,
+      "grad_norm": 0.15712368488311768,
+      "learning_rate": 1.0486058624897821e-07,
+      "loss": 2.590557861328125,
+      "step": 76500
+    },
+    {
+      "epoch": 0.007792207792207792,
+      "grad_norm": 0.14502283930778503,
+      "learning_rate": 6.717861258720426e-08,
+      "loss": 2.5785467529296877,
+      "step": 76600
+    },
+    {
+      "epoch": 0.00909090909090909,
+      "grad_norm": 0.16336509585380554,
+      "learning_rate": 3.7851188621707e-08,
+      "loss": 2.6053866577148437,
+      "step": 76700
+    },
+    {
+      "epoch": 0.01038961038961039,
+      "grad_norm": 0.1576337367296219,
+      "learning_rate": 1.6878804453168694e-08,
+      "loss": 2.595892028808594,
+      "step": 76800
+    },
+    {
+      "epoch": 0.011688311688311689,
+      "grad_norm": 0.15049995481967926,
+      "learning_rate": 4.261810558348067e-09,
+      "loss": 2.629699401855469,
+      "step": 76900
+    },
+    {
+      "epoch": 0.012987012987012988,
+      "grad_norm": 0.1851549744606018,
+      "learning_rate": 4.177841961272577e-13,
+      "loss": 2.5818411254882814,
+      "step": 77000
+    },
+    {
+      "epoch": 0.012987012987012988,
+      "eval_loss": 3.022578001022339,
+      "eval_runtime": 7.458,
+      "eval_samples_per_second": 77.233,
+      "eval_steps_per_second": 19.308,
+      "step": 77000
     }
   ],
   "logging_steps": 100,
-  "max_steps": 110000,
+  "max_steps": 77000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
   "save_steps": 4000,
@@ -5950,12 +6028,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.893508155703296e+18,
+  "total_flos": 1.918422736699392e+18,
   "train_batch_size": 22,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8c80f5d40636555b8c09ec97785c8964e446b8d757c55eb76e5b7454841939
+oid sha256:de39541c4d3c2c8cd3db89cc5a7ea96a1526b7e8be52cafa957494d7daabed0f
 size 5201