Training in progress, step 1400, checkpoint

last-checkpoint/adapter_config.json

@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "qkv_proj",
     "down_proj",
-    "o_proj",
     "gate_up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b616fe2eb021d20d4875636738be3ca7342fc6db866fd391eb53743dd565cb0
+oid sha256:070555ab40db51d3a5840454fa269b784df6d102a3f8624f43e74d58478c8951
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5356f6af8453685dfcd2ab29084ffd177cb62b8eaee4a3289a76f99910495ddc
+oid sha256:0ca946250efe75fef35aba1dbf1b03c113298722b5d7da5cedd58c3eb48dddaf
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44f04742b905a4ba4f17b43b2fddc49db3e772b856badc745872559eec73cca5
+oid sha256:354c3e84f6b2a094e741c8f1f43bff92126887859b832aecb38252864730d160
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc40c38146bda7179f03752fd8672ec7d4feef1519e7b61e194eda1f35f35156
+oid sha256:ded0d7f7cfcac928a75f77d93dbcaf43644e4251cba1e72644318143074c5e26
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4937388193202147,
+  "epoch": 0.5008944543828264,
   "eval_steps": 500,
-  "global_step": 1380,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1111,14 +1111,30 @@
       "loss": 0.4092,
       "num_input_tokens_seen": 928645,
       "step": 1380
+    },
+    {
+      "epoch": 0.49731663685152055,
+      "grad_norm": 0.3198321759700775,
+      "learning_rate": 0.00010053667262969588,
+      "loss": 0.3814,
+      "num_input_tokens_seen": 933801,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5008944543828264,
+      "grad_norm": 0.3592207133769989,
+      "learning_rate": 9.982110912343471e-05,
+      "loss": 0.3776,
+      "num_input_tokens_seen": 938905,
+      "step": 1400
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 928645,
+  "num_input_tokens_seen": 938905,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.088194664047616e+16,
+  "total_flos": 2.111265780839424e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bee6a61298e4ba0636e6bf836a1f169e31db19f42b2bb480b9f85ccd38a9c1e
+oid sha256:77d0a7fc1510ab3970debab54d5361ccc4e46d17c58f6086837651cc376b2329
 size 5048