Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38384749b3fa8fe08d6d05430325f30ab4a6dfb4936f267fce232c98c501dc69
+oid sha256:a3997e109f067717fd5f809e80f41bce891d8445f976c90d3022e49477ed45df
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:493eb904d50aba9fced0e8ab2ed8fc66ac410087d78582e9bad1afa3df987de3
+oid sha256:4920faf3068b00346c8cda8d82de2a7187b7fbdca6eefe9f18c2b04de64c9ef2
 size 5365108834

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848fdf35f13e1fde847fbd191021c99c0675e5e723a1b65fde4649f2fc9250db
+oid sha256:1e7034a159dfbc62e35de23e4c6fd1b9f4a30b049e2fbd1857b3a8bade788440
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f9fc41c0627d630837221d5c7872d3197c08985ee35f058d5f5e36bfe0249b
+oid sha256:cc2ced66205bf6a6509c630ed58ad5e3a6e3843df72048f8b326021e9e36307f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ae1449d711371210b0f6284f921f3df183a3c5c6628d3fc2950f5c89910866d
+oid sha256:753dcfeefdbe4107c04bfd9f26c44afd642bd34e5d3d0b685a1b7e09f489639e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3cc14e80a0475fa4dead8d6a3c6f0af9c5a92c40ad285584d68830834b3a6ea
+oid sha256:3e87981ec44568bc91dcff3b2572db474da39ce05df9ab33e26b3f375f4eac1b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478ca537cf75a11344e25e46d3c46fdcf2db572bdb8cfff6f1ed3781e47a9787
+oid sha256:b6956522915b3d6cfb4a36d77fb3f2d3b9a7b7a09c560fa745829757b1d0d295
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03836047336824137,
+  "epoch": 0.07672094673648273,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,76 @@
       "learning_rate": 9.616387908546877e-05,
       "loss": 69.615,
       "step": 500
+    },
+    {
+      "epoch": 0.0421965207050655,
+      "grad_norm": 32.29951858520508,
+      "learning_rate": 9.578026699401565e-05,
+      "loss": 69.3197,
+      "step": 550
+    },
+    {
+      "epoch": 0.046032568041889634,
+      "grad_norm": 47.040401458740234,
+      "learning_rate": 9.539665490256254e-05,
+      "loss": 69.4096,
+      "step": 600
+    },
+    {
+      "epoch": 0.049868615378713774,
+      "grad_norm": 15.688956260681152,
+      "learning_rate": 9.501304281110941e-05,
+      "loss": 68.8061,
+      "step": 650
+    },
+    {
+      "epoch": 0.05370466271553791,
+      "grad_norm": 47.72418212890625,
+      "learning_rate": 9.462943071965629e-05,
+      "loss": 68.8162,
+      "step": 700
+    },
+    {
+      "epoch": 0.05754071005236205,
+      "grad_norm": 60.38280487060547,
+      "learning_rate": 9.424581862820317e-05,
+      "loss": 68.3997,
+      "step": 750
+    },
+    {
+      "epoch": 0.06137675738918618,
+      "grad_norm": 18.39830207824707,
+      "learning_rate": 9.386220653675004e-05,
+      "loss": 68.264,
+      "step": 800
+    },
+    {
+      "epoch": 0.06521280472601032,
+      "grad_norm": 55.10166931152344,
+      "learning_rate": 9.347859444529692e-05,
+      "loss": 67.9374,
+      "step": 850
+    },
+    {
+      "epoch": 0.06904885206283445,
+      "grad_norm": 28.2165584564209,
+      "learning_rate": 9.309498235384379e-05,
+      "loss": 67.6585,
+      "step": 900
+    },
+    {
+      "epoch": 0.07288489939965859,
+      "grad_norm": 43.54179763793945,
+      "learning_rate": 9.271137026239067e-05,
+      "loss": 67.4189,
+      "step": 950
+    },
+    {
+      "epoch": 0.07672094673648273,
+      "grad_norm": 25.794546127319336,
+      "learning_rate": 9.232775817093756e-05,
+      "loss": 67.0964,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -96,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.568157303923016e+17,
+  "total_flos": 1.7134867976961393e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null