Training in progress, step 1680, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "qkv_proj",
-    "down_proj",
-    "gate_up_proj"
+    "o_proj",
+    "gate_up_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee715368403bed92f0597eabc44753fd00d49356f11cef1b3c8fb8c0804ae158
+oid sha256:bd9525a4c9388eba206599ad1083c9f04830f7c0993ba71f7249c50d3c13d194
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:208b124f35b0f1bb89c24aa5e442cf97e514521b89c0892c0bc2dd2ca24dcc7c
+oid sha256:dc517b5ef5e5fb65e842afb1ff46711a33890ca508092071a4522eec551c4860
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba8cf0f8aa521d1f1829b6d195f2417168669d9a3f3f5d0131830f8caf9a53ed
+oid sha256:2111ebc063da3a4cacd27c844d6c3c4ea5d6c8b4612b9ccfbb113e1022b25f1b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f76a6b8811ac3433e0a8dcf8c698d49602a1ab3ba3e9478d0943f2dd2665d0e5
+oid sha256:f6f33bde628cfaa59f6d1470858dd0b46ed4d4b40c45bae4e5eb4771b5d21f15
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.59391771019678,
+  "epoch": 0.6010733452593918,
   "eval_steps": 500,
-  "global_step": 1660,
+  "global_step": 1680,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1335,14 +1335,30 @@
       "loss": 0.3903,
       "num_input_tokens_seen": 1115112,
       "step": 1660
+    },
+    {
+      "epoch": 0.5974955277280859,
+      "grad_norm": 0.39852896332740784,
+      "learning_rate": 8.050089445438284e-05,
+      "loss": 0.4128,
+      "num_input_tokens_seen": 1121451,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6010733452593918,
+      "grad_norm": 0.37065914273262024,
+      "learning_rate": 7.978533094812165e-05,
+      "loss": 0.4015,
+      "num_input_tokens_seen": 1129374,
+      "step": 1680
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1115112,
+  "num_input_tokens_seen": 1129374,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.5074930982404096e+16,
+  "total_flos": 2.539563299769139e+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 sha256:77d0a7fc1510ab3970debab54d5361ccc4e46d17c58f6086837651cc376b2329
+oid sha256:b6627f5a0391650843e3b66a870c0689d2522bb2ec40028b633e06c7aaaaff6d
 size 5048