Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8537667eb2c1590a1b2a1c34f2de9292e65cc7ace043f57a94bbce298c07cee
+oid sha256:b1beb7f2e0502feb6586b3268e2aa339af5bb5b1aecdba28220efe9b86e05aab
 size 183784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff737ce4bd3480df082e35a2ceac05f083a433be3eb3fc3fc4b55760a97bcda
+oid sha256:22bcbbecdb02b3cbb28f48bb4653f48180a818d709bea369f228efcf4523d050
 size 236760

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db3e559c298d4a2aa71fc2be31e00e408588329761236aec5fe912fd29d2384d
+oid sha256:1bb812854271d2dd6f5d1621a16e346cd2a930ab781f162177c7455f20c7291c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7417d3df19f914d5ff3de50e1ce3e883c2e459b2dba528703683d4a328a4e0f
+oid sha256:8bf0f7c6ecc3ac28466ea76bb6b708b78e42abd3fbd5d001417b73e948d81162
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c3395b638fca0417167bebc767ae35bf6c7bb1a639f0851b624a26e9c08419e
+oid sha256:d159cb47b8d829628c4baba13b9b0791bfd74ecb5fa0e98be732c166ae850c2f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f14ae5014776de6223329b6dc8f9efc58d39f88f71b06e9dacbef3ff996556e
+oid sha256:6c040133306db04c9d19ef87920c336e46502a4a93e9907439fe79475367d13b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab4ba69e83f65129bdf14a330e6b14308f6903214fa4aa747256ae7ff2c663e
+oid sha256:f3400db4ad22089f92d8cb2575defb82bd326765413235c180f06a5c672c23bc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7586206896551726,
+  "epoch": 4.137931034482759,
   "eval_steps": 16,
-  "global_step": 80,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,6 +111,50 @@
       "eval_samples_per_second": 170.691,
       "eval_steps_per_second": 6.782,
       "step": 80
+    },
+    {
+      "epoch": 3.103448275862069,
+      "grad_norm": 0.017773684114217758,
+      "learning_rate": 4.381536843653262e-05,
+      "loss": 11.9181,
+      "step": 90
+    },
+    {
+      "epoch": 3.310344827586207,
+      "eval_loss": 11.915090560913086,
+      "eval_runtime": 0.9023,
+      "eval_samples_per_second": 167.348,
+      "eval_steps_per_second": 6.65,
+      "step": 96
+    },
+    {
+      "epoch": 3.4482758620689653,
+      "grad_norm": 0.02540409192442894,
+      "learning_rate": 3.3765026539765834e-05,
+      "loss": 11.9176,
+      "step": 100
+    },
+    {
+      "epoch": 3.793103448275862,
+      "grad_norm": 0.022573214024305344,
+      "learning_rate": 2.4405747545519963e-05,
+      "loss": 11.9175,
+      "step": 110
+    },
+    {
+      "epoch": 3.862068965517241,
+      "eval_loss": 11.91474723815918,
+      "eval_runtime": 0.8995,
+      "eval_samples_per_second": 167.874,
+      "eval_steps_per_second": 6.67,
+      "step": 112
+    },
+    {
+      "epoch": 4.137931034482759,
+      "grad_norm": 0.02882819063961506,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 11.9174,
+      "step": 120
     }
   ],
   "logging_steps": 10,
@@ -130,7 +174,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1295001845760.0,
+  "total_flos": 1942502768640.0,
   "train_batch_size": 7,
   "trial_name": null,
   "trial_params": null